Publications

@inproceedings{lemercier2026diladiff,
  title = {{DiLaDiff: Distilled Latent-augmented Diffusion for Language Modeling}},
  author = {Jean-Marie Lemercier and Tomas Geffner and Morteza Mardani and Karsten Kreis and Arash Vahdat and Ante Jukić},
  year = {2026},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2605.23605},
  archiveprefix = {arxiv},
}

@inproceedings{hatamizadeh2026gdn2,
  title = {Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention},
  author = {Ali Hatamizadeh and Yejin Choi and Jan Kautz},
  year = {2026},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2605.22791},
  archiveprefix = {arxiv},
}

@inproceedings{duisterhof2026PointZero,
  title = {{PointZero}: {3D} Point Track Completion for Learning Transferable {3D} Dynamics},
  author = {Bardienus Pieter Duisterhof and Kaifeng Zhang and Adam Hung and Bowen Wen and Stan Birchfield and Yunzhu Li and Deva Ramanan and Jeffrey Ichnowski},
  year = {2026},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2609.19142},
  archiveprefix = {arxiv},
}

@inproceedings{sabour2026fmtt,
  title = {{Test-time Scaling of Diffusions with Flow Maps}},
  author = {Amirmojtaba Sabour and Michael Samuel Albergo and Carles Domingo-Enrich and Nicholas Matthew Boffi and Sanja Fidler and Karsten Kreis and Eric Vanden-Eijnden},
  year = {2026},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2511.22688},
  archiveprefix = {arxiv},
}

@inproceedings{wu2026addressable,
  title = {Addressable Memory for Video World Models},
  author = {Wu, Xindi and Elflein, Sven and Lucas, James and Russakovsky, Olga and Leal-Taixé, Laura and Paschalidou, Despoina and Lorraine, Jonathan and Ošep, Aljoša},
  year = {2026},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2608.07408},
  archiveprefix = {arXiv},
}

@inproceedings{li2026nemotron,
  title = {Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis},
  author = {Li, Shufan and Heinrich, Greg and Ye, Hanrong and Fu, Yonggan and Grover, Aditya and Kautz, Jan and Molchanov, Pavlo},
  year = {2026},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2606.29814},
  archiveprefix = {arxiv},
}

@inproceedings{bettencourt2026carv,
  title = {Variance Reduction for Expectations with Diffusion Teachers},
  author = {Bettencourt, Jesse and Wu, Xindi and Atzmon, Matan and Lucas, James and Lorraine, Jonathan},
  year = {2026},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2605.21489},
  archiveprefix = {arXiv},
}

@article{Butcher2026RFdiffusion3,
  title = {Atomic functional site scaffolding in biopolymers with {RFdiffusion3}},
  author = {Butcher, Jasper and Krishna, Rohith and Mitra, Raktim and
             Woodbury, Seth M. and Kim, Donghyo and Brent, Rafael I. and
             Li, Yanjing and Corley, Nathaniel and Favor, Andrew and
             Chen, Anqi and Kim, Paul T. and Funk, Jonathan and
             Bastidas Reinoso, Gabriela and Wu, Kejia and Muraishi, Aiko and
             Eisenach, Helen E. and Salike, Saman and Mathis, Simon and
             Thompson, Tuscan Rock and Ruder, Antonia and Sehgal, Enisha and
             Kubaney, Andrew and Chen, Jie and Politanska, Yuliya and
             Coventry, Brian and Zhang, Odin and Hardy, Florence J. and
             Qiang, Bo and Didi, Kieran and Kazman, Maxwell and
             DiMaio, Frank and Baker, David},
  year = {2026},
  month = {oct},
  journal = {Science},
  doi = {10.1126/science.aeh2982},
}

@article{Chen2026Metalloproteases,
  title = {Computational design of metalloproteases},
  author = {Chen, Anqi and Wu, Kejia and Choi, Hojae and
             Venkatesh, Preetham and Pellock, Samuel J. and
             Hanikel, Nikita and Shin, Hojeong and Evans, Declan and
             Didi, Kieran and Schaaf, Lars L. and
             D{\'i}az-Perlas, Cristina and Coventry, Brian and
             Kim, Donghyo and Woodbury, Seth M. and Ji, Pengfei and
             Honda, Shingo and Bera, Asim K. and Nguyen, Hannah and
             Kang, Alex and Wang, Yanqing and Li, Xinting and
             Gerben, Stacey and Chang, Lemuel and Yan, Xiao and
             Oller-Salvia, Benjam{\'i} and Hyman, Anthony A. and
             Hilvert, Donald and Baker, David},
  year = {2026},
  month = {oct},
  journal = {Nature},
  doi = {10.1038/s41586-026-11167-2},
}

@article{Choi2026CysteineProteases,
  title = {De novo design of cysteine proteases},
  author = {Choi, Hojae and Bauer, Magnus S. and Coventry, Brian and
             Venkatesh, Preetham and Chen, Anqi and Kim, Donghyo and
             Bera, Asim K. and Kang, Alex and Nguyen, Hannah and
             Sadre, Shayan and Decarreau, Justin and Joyce, Emily and
             Shankaran, Bhanumathi and Thompson, Tuscan Rock and
             Greenstein, Gabriel and Didi, Kieran and Schaaf, Lars L. and
             Gershon, Jacob Merle and Shida, Alexander F. and
             Lee, Gyu Rie and Hilvert, Donald and Pellock, Samuel J. and
             Baker, David},
  year = {2026},
  month = {oct},
  journal = {Nature},
  doi = {10.1038/s41586-026-11143-w},
}

@inproceedings{teufel2026drex,
  title = {D-Rex: Diffusion Rendering for Relightable Expressive Avatars},
  author = {Timo Teufel and Xilong Zhou and Umar Iqbal and Jan Kautz and Marc Habermann and Vladislav Golyanik and Christian Theobalt},
  year = {2026},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2604.27871},
  archiveprefix = {arxiv},
}

@inproceedings{wang2026parallelbox,
  title = {LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding},
  author = {Shihao Wang and Shilong Liu and Yuanguo Kuang and Xinyu Wei and Yangzhou Liu and Zhiqi Li and Yunze Man and Guo Chen and Andrew Tao and Guilin Liu and Jan Kautz and Lei Zhang and Zhiding Yu},
  year = {2026},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2605.27365},
  archiveprefix = {arxiv},
}

@article{lee2026dmp,
  title = {DMP: Directable Motion Retargeting through Motion Paraphrasing},
  author = {Lee, Sunmin and Rempe, Davis and Jiang, Yifeng and Zhang, Haotian and Wang, Tingwu and Won, Jungdam and Peng, Xue Bin},
  year = {2026},
  month = {September},
  journal = {ACM Transactions on Graphics (ToG)},
  volume = {46},
  number = {1},
  pages = {1--16},
  doi = {10.1145/3829359},
}

@article{SONIC2026,
  title = {SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control},
  author = {Zhengyi Luo  and Ye Yuan  and Tingwu Wang  and Chenran Li  and Fernando Castañeda  and Sirui Chen  and Zi-Ang Cao  and Jiefeng Li  and David Minor  and Qingwei Ben  and Jinhyung Park  and David Sami  and Zi Wang  and Xingye Da  and Runyu Ding  and Cyrus Hogg  and Lina Song  and Edy Lim  and Eugene Jeong  and Tairan He  and Haoru Xue  and Wenli Xiao  and Simon Yuen  and Jan Kautz  and Yan Chang  and Umar Iqbal  and Linxi Fan  and Yuke Zhu},
  year = {2026},
  month = {August},
  journal = {Science Robotics},
  volume = {11},
  number = {117},
  doi = {10.1126/scirobotics.aed4592},
  eprint = {2511.07820},
  archiveprefix = {arxiv},
}

@misc{hu2026molt,
  title = {Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning},
  author = {Jian Hu and Huiying Li and Hao Zhang and Binfeng Xu and Yifan Zhang and Shaokun Zhang and Hemil Desai and Michael Demoret and Pavlo Molchanov and Jan Kautz and Yi Dong},
  year = {2026},
  month = {July},
  eprint = {2607.21653},
  archiveprefix = {arxiv},
}

@inproceedings{shi2026gpc,
  title = {GPC: Large-Scale Generative Pretraining for Transferable Motor Control},
  author = {Shi, Yi and Jiang, Yifeng and Tessler, Chen and Peng, Xue Bin},
  year = {2026},
  month = {July},
  booktitle = {Proceedings of SIGGRAPH},
  pages = {1--11},
  doi = {10.1145/3799902.3811038},
  eprint = {2606.29148},
  archiveprefix = {arxiv},
}

@inproceedings{yang2026robolab,
  title = {RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies},
  author = {Yang, Xuning and Dagli, Rishit and Zook, Alex and Hadfield, Hugo and Goyal, Ankit and Birchfield, Stan and Ramos, Fabio and Tremblay, Jonathan},
  year = {2026},
  month = {July},
  booktitle = {Robotics: Science and Systems (RSS)},
  eprint = {2604.09860},
  archiveprefix = {arxiv},
}

@inproceedings{heinrich2026radio1d,
  title = {RADIO1D: Elastic Representations for Condensed Vision Modeling},
  author = {Greg Heinrich and Mike Ranzinger and Collin McCarthy and Natan Bagrov and Eugene Khvedchenya and Bryan Catanzaro and Jan Kautz and Andrew Tao and Pavlo Molchanov},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2607.03624},
  archiveprefix = {arxiv},
}

@inproceedings{ma2026flex,
  title = {Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model},
  author = {Xinyin Ma and Julius Berner and Chao Liu and Arash Vahdat and Weili Nie and Xinchao Wang},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2607.03509},
  archiveprefix = {arxiv},
}

@inproceedings{sahoo2026esoteric,
  title = {{Esoteric Language Models: A Family of Any-Order Diffusion LLMs}},
  author = {Subham Sekhar Sahoo and Zhihan Yang and Yash Akhauri and Johnna Liu and Deepansha Singh and Zhoujun Cheng and Zhengzhong Liu and Eric Xing and John Thickstun and Arash Vahdat},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
}

@inproceedings{taghibakhshi2026starelastic,
  title = {Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control},
  author = {Ali Taghibakhshi and Ruisi Cai and Saurav Muralidharan and Sharath Turuvekere Sreenivas and Aditya Vavre and Ameya Sunil Mahabaleshwarkar and Bilal Kartal and Sheldon Liang and Marcin Chochowski and Zijia Chen and Akhiad Bercovich and Ran Zilberstein and Ran El-Yaniv and Yonatan Geifman and Daniel Korzekwa and Yoshi Suhara and Oluwatobi Olabiyi and Ashwath Aithal and Nima Tajbakhsh and Pavlo Molchanov},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2605.07182},
  archiveprefix = {arxiv},
}

@inproceedings{choy2026spaceformer,
  title = {SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation},
  author = {Chris Choy and Junha Lee and Chunghyun Park and Minsu Cho and Jan Kautz},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2604.20395},
  archiveprefix = {arxiv},
}

@inproceedings{cai2026mode,
  title = {Mode Seeking meets Mean Seeking for Fast Long Video Generation},
  author = {Shengqu Cai and Weili Nie and Chao Liu and Julius Berner and Lvmin Zhang and Nanye Ma and Hansheng Chen and Maneesh Agrawala and Leonidas Guibas and Gordon Wetzstein and Arash Vahdat},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2602.24289},
  archiveprefix = {arxiv},
}

@inproceedings{lu2026goldengoose,
  title = {Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text},
  author = {Ximing Lu and David Acuna and Jaehun Jung and Jian Hu and Di Zhang and Shizhe Diao and Yunheng Zou and Shaokun Zhang and Brandon Cui and Mingjie Liu and Hyunwoo Kim and Prithviraj Ammanabrolu and Jan Kautz and Yi Dong and Yejin Choi},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2601.22975},
  archiveprefix = {arxiv},
}

@inproceedings{learningTTT2026,
  title = {Learning to Discover at Test Time},
  author = {Mert Yuksekgonul and Daniel Koceja and Xinhao Li and Federico Bianchi and Jed McCaleb and Xiaolong Wang and Jan Kautz and Yejin Choi and James Zou and Carlos Guestrin and Yu Sun},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2601.16175},
  archiveprefix = {arxiv},
}

@inproceedings{liu2026gdpo,
  title = {GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization},
  author = {Shih-Yang Liu and Xin Dong and Ximing Lu and Shizhe Diao and Peter Belcak and Mingjie Liu and Min-Hung Chen and Hongxu Yin and Yu-Chiang Frank Wang and Kwang-Ting Cheng and Yejin Choi and Jan Kautz and Pavlo Molchanov},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2601.05242},
  archiveprefix = {arxiv},
}

@inproceedings{efficientdlm2026,
  title = {Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed},
  author = {Yonggan Fu and Lexington Whalen and Zhifan Ye and Xin Dong and Shizhe Diao and Jingyu Liu and Chengyue Wu and Hao Zhang and Enze Xie and Song Han and Maksim Khadkevich and Jan Kautz and Yingyan Lin and Pavlo Molchanov},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2512.14067},
  archiveprefix = {arxiv},
}

@inproceedings{toolorchestra2026,
  title = {ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration},
  author = {Hongjin SU and Shizhe Diao and Ximing Lu and Mingjie Liu and Jiacheng Xu and Xin Dong and Yonggan Fu and Peter Belcak and Hanrong Ye and Hongxu Yin and Yi Dong and Evelina Bakhturina and Tao Yu and Yejin Choi and Jan Kautz and Pavlo Molchanov},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2511.21689},
  archiveprefix = {arxiv},
}

@inproceedings{brorl2026,
  title = {BroRL: Scaling Reinforcement Learning via Broadened Exploration},
  author = {Jian Hu and Mingjie Liu and Ximing Lu and Fang Wu and Zaid Harchaoui and Shizhe Diao and Yejin Choi and Pavlo Molchanov and Jun Yang and Jan Kautz and Yi Dong},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2510.01180},
  archiveprefix = {arxiv},
}

@misc{fu2026nemotron,
  title = {Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding},
  author = {Yonggan Fu and Lexington Whalen and Abhinav Garg and Chengyue Wu and Maksim Khadkevich and Nicolai Oswald and Enze Xie and Daniel Egert and Sharath Turuvekere Sreenivas and Shizhe Diao and Chenhan Yu and Ye Yu and Weijia Chen and Sajad Norouzi and Jingyu Liu and Shiyi Lan and Ligeng Zhu and Jin Wang and Jindong Jiang and Morteza Mardani and Mehran Maghoumi and Song Han and Ante Jukić and Nima Tajbakhsh and Jan Kautz and Pavlo Molchanov},
  year = {2026},
  eprint = {2607.05722},
  archiveprefix = {arxiv},
}

@article{zhao2026ardy,
  title = {ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation},
  author = {Zhao, Kaifeng and Petrovich, Mathis and Zhang, Haotian and Wang, Tingwu and Tang, Siyu and Rempe, Davis},
  year = {2026},
  month = {July},
  journal = {ACM Transactions on Graphics (ToG)},
  volume = {45},
  number = {4},
  pages = {1--14},
  doi = {10.1145/3811284},
  eprint = {2607.08741},
  archiveprefix = {arxiv},
}

@article{wang2026hil,
  title = {HIL: Hybrid Imitation Learning for Dynamic Athletic Control},
  author = {Wang, Jiashun and Jiang, Yifeng and Zhang, Haotian and Tessler, Chen and Rempe, Davis and Hodgins, Jessica and Peng, Xue Bin},
  year = {2026},
  month = {July},
  journal = {ACM Transactions on Graphics (ToG)},
  doi = {10.1145/3829364},
  eprint = {2505.12619},
  archiveprefix = {arxiv},
}

@article{wang2026motionbricks,
  title = {MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives},
  author = {Tingwu Wang and Olivier Dionne and Michael De Ruyter and David Minor and Davis Rempe and Kaifeng Zhao and Mathis Petrovich and Ye Yuan and Chenran Li and Zhengyi Luo and Brian Robison and Xavier Blackwell and Bernardo Antoniazzi and Xue Bin Peng and Yuke Zhu and Simon Yuen},
  year = {2026},
  month = {July},
  journal = {ACM Transactions on Graphics (ToG)},
  volume = {45},
  number = {4},
  pages = {1--22},
  doi = {10.1145/3811334},
  eprint = {2604.24833},
  archiveprefix = {arxiv},
}

@misc{wang2026presto,
  title = {PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding},
  author = {Zheng Wang and Zhifan Ye and Qi Cheng and Yonggan Fu and Ziyan Wang and Feng Zhu and Haozhe Zhao and Jan Kautz and Pavlo Molchanov and Humphrey Shi and Minjia Zhang},
  year = {2026},
  month = {June},
  eprint = {2607.22634},
  archiveprefix = {arxiv},
}

@inproceedings{cho2026vlm4dp,
  title = {4DP-QA: Scalable QA for 4D Perception in Vision Language Models},
  author = {Seokju Cho and Abhishek Badki and Hang Su and Jindong Jiang and Ziyao Zeng and Seungryong Kim and Sifei Liu and Orazio Gallo},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
}

@inproceedings{compactGSPN2025,
  title = {Scaling Parallel Sequence Models to Vision Foundation Models},
  author = {Yitong Jiang and Collin McCarthy and Hongjun Wang and Hanrong Ye and Qi Dou and Tianfan Xue and Jinwei Gu and Jan Kautz and Hongxu Yin and Pavlo Molchanov and Sifei Liu},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
}

@inproceedings{han2025graspgenx,
  title = {{GraspGen-X}: Cross-Embodiment 6-DOF Diffusion-based Grasping},
  author = {Beining Han and Yu-Wei Chao and Erwin Coumans and Clemens Eppner and Balakumar Sundaralingam and Jia Deng and Stan Birchfield and Adithyavairavan Murali},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2606.00998},
  archiveprefix = {arxiv},
}

@inproceedings{cheng2026grounded,
  title = {Grounded 3D-Aware Spatial Vision-Language Modeling},
  author = {Cheng, An-Chieh and Fu, Yang and Ji, Yatai and Zhu, Ligeng and Zhan, Guanqi and Zhang, Zhuoyang and Yang, Zhaojing and Han, Song and Lu, Yao and Molchanov, Pavlo and Murali, Vidya Nariyambut and Kautz, Jan and Wang, Xiaolong and Yin, Hongxu and Liu, Sifei},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2605.30307},
  archiveprefix = {arxiv},
}

@inproceedings{shi2026autogaze,
  title = {Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing},
  author = {Baifeng Shi and Stephanie Fu and Long Lian and Hanrong Ye and David Eigen and Aaron Reite and Boyi Li and Jan Kautz and Song Han and David M. Chan and Pavlo Molchanov and Trevor Darrell and Hongxu Yin},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2603.12254},
  archiveprefix = {arxiv},
}

@inproceedings{xiong2026phycritic,
  title = {PhyCritic: Multimodal Critic Models for Physical AI},
  author = {Tianyi Xiong and Shihao Wang and Guilin Liu and Yi Dong and Ming Li and Heng Huang and Jan Kautz and Zhiding Yu},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2602.11124},
  archiveprefix = {arxiv},
}

@inproceedings{nie2025transition,
  title = {Transition Matching Distillation for Fast Video Generation},
  author = {Weili Nie and Julius Berner and Nanye Ma and Chao Liu and Saining Xie and Arash Vahdat},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2601.09881},
  archiveprefix = {arxiv},
}

@inproceedings{huang2026fastthinkact,
  title = {Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning},
  author = {Chi-Pin Huang and Yunze Man and Zhiding Yu and Min-Hung Chen and Jan Kautz and Yu-Chiang Frank Wang and Fu-En Yang},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2601.09708},
  archiveprefix = {arxiv},
}

@inproceedings{magne2026nitrogenopenfoundationmodel,
  title = {NitroGen: An Open Foundation Model for Generalist Gaming Agents},
  author = {Lo\"{i}c Magne and Anas Awadalla and Guanzhi Wang and Yinzhen Xu and Joshua Belofsky and Fengyuan Hu and Joohwan Kim and Ludwig Schmidt and Georgia Gkioxari and Jan Kautz and Yisong Yue and Yejin Choi and Yuke Zhu and Linxi Fan},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2601.02427},
  archiveprefix = {arXiv},
}

@inproceedings{park2026m3kgrag,
  title = {M^3KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation},
  author = {Hyeongcheol Park and Jiyoung Seo and Jaewon Mun and Hogun Park and Wonmin Byeon and Sung June Kim and Hyeonsoo Im and JeungSub Lee and Sangpil Kim},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2512.20136},
  archiveprefix = {arxiv},
}

@inproceedings{xie2026cari4d,
  title = {{CARI4D}: Category Agnostic {4D} Reconstruction of Human-Object Interaction},
  author = {Xie, Xianghui and Wen, Bowen and Chang, Yan and Rabeti, Hesam and Li, Jiefeng and Yuan, Ye and Pons-Moll, Gerard and Birchfield, Stan},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2512.11988},
  archiveprefix = {arxiv},
}

@inproceedings{wen2026fastfoundationstereo,
  title = {{Fast-FoundationStereo}: Real-Time Zero-Shot Stereo Matching},
  author = {Wen, Bowen and Dewan, Shaurya Rajat and Birchfield, Stan},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2512.11130},
  archiveprefix = {arxiv},
}

@inproceedings{chen2026spacetools,
  title = {{SpaceTools}: Tool-Augmented Spatial Reasoning via Double Interactive {RL}},
  author = {Chen, Siyi and Uy, Mikaela Angelina and Song, Chan Hee and Ladhak, Faisal and Murali, Adithyavairavan and Qu, Qing and Birchfield, Stan and Blukis, Valts and Tremblay, Jonathan},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2512.04069},
  archiveprefix = {arxiv},
}

@inproceedings{xue2026opening,
  title = {Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer},
  author = {Xue, Haoru and He, Tairan and Wang, Zi and Ben, Qingwei and Xiao, Wenli and Luo, Zhengyi and Da, Xingye and Casta{\~n}eda, Fernando and Shi, Guanya and Sastry, Shankar and Fan, Linxi and Zhu, Yuke},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2512.01061},
  archiveprefix = {arxiv},
}

@inproceedings{man2026locateanything3d,
  title = {LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight},
  author = {Yunze Man and Shihao Wang and Guowen Zhang and Johan Bjorck and Zhiqi Li and Liang-Yan Gui and Linxi Fan and Jan Kautz and Yu-Xiong Wang and Zhiding Yu},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2511.20648},
  archiveprefix = {arxiv},
}

@inproceedings{pallotta2026egocontrol,
  title = {EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses},
  author = {Enrico Pallotta and Sina Mokhtarzadeh Azar and Lars Doorenbos and Serdar Ozsoy and Umar Iqbal and Juergen Gall},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2511.18173},
  archiveprefix = {arxiv},
}

@inproceedings{bhat2026bopask,
  title = {{BOP-ASK}: Object-Interaction Reasoning for Vision-Language Models},
  author = {Bhat, Vineet and Kim, Sungsu and Blukis, Valts and Heinrich, Greg and Krishnamurthy, Prashanth and Karri, Ramesh and Birchfield, Stan and Khorrami, Farshad and Tremblay, Jonathan},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2511.16857},
  archiveprefix = {arxiv},
}

@inproceedings{he2026viral,
  title = {VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation},
  author = {He, Tairan and Wang, Zi and Xue, Haoru and Ben, Qingwei and Luo, Zhengyi and Xiao, Wenli and Yuan, Ye and Da, Xingye and Casta{\~n}eda, Fernando and Sastry, Shankar and Liu, Changliu and Shi, Guanya and Fan, Linxi and Zhu, Yuke},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2511.15200},
  archiveprefix = {arxiv},
}

@inproceedings{wang2025videoitg,
  title = {VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding},
  author = {Shihao Wang and Guo Chen and De-An Huang and Zhiqi Li and Minghan Li and Guilin Liu and Jan Kautz and Jose M. Alvarez and Lei Zhang and Zhiding Yu},
  year = {2026},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2507.13353},
  archiveprefix = {arxiv},
}

@inproceedings{tang2026refinery,
  title = {{Refinery}: Active Fine-tuning and Deployment-time Optimization for Contact-Rich Policies},
  author = {Bingjie Tang and Iretiayo Akinola and Jie Xu and Bowen Wen and Michael Andres Lin and Dieter Fox and Gaurav S. Sukhatme and Fabio Ramos and Abhishek Gupta and Yashraj Narang},
  year = {2026},
  month = {June},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2510.11019},
  archiveprefix = {arxiv},
}

@inproceedings{yamada2026graspmpc,
  title = {{Grasp-MPC}: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control},
  author = {Jun Yamada and Adithyavairavan Murali and Ajay Mandlekar and Clemens Eppner and Ingmar Posner and Balakumar Sundaralingam},
  year = {2026},
  month = {June},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2509.06201},
  archiveprefix = {arxiv},
}

@inproceedings{murali2026graspgen,
  title = {{GraspGen}: A Diffusion-based Framework for {6-DOF} Grasping with On-Generator Training},
  author = {Adithyavairavan Murali and Balakumar Sundaralingam and Yu-Wei Chao and Wentao Yuan and Jun Yamada and Mark Carlson and Fabio Ramos and Stan Birchfield and Dieter Fox and Clemens Eppner},
  year = {2026},
  month = {June},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2507.13097},
  archiveprefix = {arxiv},
}

@inproceedings{complexa2026,
  title = {Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute},
  author = {Kieran Didi and Zuobai Zhang and Guoqing Zhou and Danny Reidenbach and Zhonglin Cao and Sooyoung Cha and Tomas Geffner and Christian Dallago and Jian Tang and Michael M. Bronstein and Martin Steinegger and Emine Kucukbenli and Arash Vahdat and Karsten Kreis},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2603.27950},
  archiveprefix = {arxiv},
}

@inproceedings{profbench2026,
  title = {ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge},
  author = {Zhilin Wang and Jaehun Jung and Ximing Lu and Shizhe Diao and Ellie Evans and Jiaqi Zeng and Pavlo Molchanov and Yejin Choi and Jan Kautz and Yi Dong},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2510.18941},
  archiveprefix = {arxiv},
}

@inproceedings{omnivinci2026,
  title = {OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM},
  author = {Hanrong Ye and Chao-Han Huck Yang and Arushi Goel and Wei Huang and Zhen Wan and Jinchuan Tian and An-Chieh Cheng and Ligeng Zhu and Yuanhang Su and Yuming Lou and Yong-Xiang Lin and Dong Yang and Sreyan Ghosh and Zhijian Liu and Yukang Chen and Ehsan Jahangiri and Ambrish Dantrey and Daguang Xu and Ehsan Hosseini-Asl and Seyed Danial Mohseni Taheri and Vidya Nariyambut Murali and Sifei Liu and Yao Lu and Oluwatobi Olabiyi and Yu-Chiang Frank Wang and Rafael Valle and Bryan Catanzaro and Andrew Tao and Song Han and Jan Kautz and Hongxu Yin and Pavlo Molchanov},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2510.15870},
  archiveprefix = {arxiv},
}

@inproceedings{hatamizadeh2025rlp,
  title = {RLP: Reinforcement as a Pretraining Objective},
  author = {Ali Hatamizadeh and Syeda Nahida Akter and Shrimai Prabhumoye and Jan Kautz and Mostofa Patwary and Mohammad Shoeybi and Bryan Catanzaro and Yejin Choi},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2510.01265},
  archiveprefix = {arxiv},
}

@inproceedings{reasyn2026,
  title = {Exploring Synthesizable Chemical Space with Iterative Pathway Refinements},
  author = {Seul Lee and Karsten Kreis and Srimukh Prasad Veccham and Meng Liu and Danny Reidenbach and Saee Gopal Paliwal and Weili Nie and Arash Vahdat},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2509.16084},
  archiveprefix = {arxiv},
}

@inproceedings{cheng20253dawareVLM,
  title = {3D Aware Region Prompted Vision Language Model},
  author = {An-Chieh Cheng and Yang Fu and Yukang Chen and Zhijian Liu and Xiaolong Li and Subhashree Radhakrishnan and Song Han and Yao Lu and Jan Kautz and Pavlo Molchanov and Hongxu Yin and Xiaolong Wang and Sifei Liu},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2509.13317},
  archiveprefix = {arxiv},
}

@inproceedings{laproteina2025,
  title = {La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching},
  author = {Tomas Geffner and Kieran Didi and Zhonglin Cao and Danny Reidenbach and Zuobai Zhang and Christian Dallago and Emine Kucukbenli and Karsten Kreis and Arash Vahdat},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2507.09466},
  archiveprefix = {arxiv},
}

@inproceedings{zhang2025tooln1,
  title = {Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning},
  author = {Shaokun Zhang and Yi Dong and Jieyu Zhang and Jan Kautz and Bryan Catanzaro and Andrew Tao and Qingyun Wu and Zhiding Yu and Guilin Liu},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2505.00024},
  archiveprefix = {arxiv},
}

@inproceedings{zou2026recursivemas,
  title = {Recursive Multi-Agent Systems},
  author = {Jiaru Zou and Rui Pan and Ruizhong Qiu and Pan Lu and Shizhe Diao and Jindong Jiang and Hanghang Tong and Tong Zhang and Markus J. Buehler and Jingrui He and James Zou},
  year = {2026},
  month = {April},
  booktitle = {ArXiv Preprint},
  eprint = {2604.25917},
  archiveprefix = {arxiv},
}

@inproceedings{Buehler2025dla,
  title = {Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars},
  author = {Marcel Buehler and Ye Yuan and Xueting Li and Yangyi Huang and Koki Nagano and Umar Iqbal},
  year = {2026},
  month = {March},
  booktitle = {International Conference on 3D Vision (3DV)},
  eprint = {2507.15979},
  archiveprefix = {arxiv},
}

@inproceedings{badki2025l4p,
  title = {{L4P}: Towards Unified Low-Level {4D} Vision Perception},
  author = {Abhishek Badki and Hang Su and Bowen Wen and Orazio Gallo},
  year = {2026},
  month = {March},
  booktitle = {International Conference on 3D Vision (3DV)},
  eprint = {2502.13078},
  archiveprefix = {arxiv},
}

@misc{saito2026soma,
  title = {SOMA: Unifying Parametric Human Body Models},
  author = {Jun Saito and Jiefeng Li and Michael de Ruyter and Miguel Guerrero and Edy Lim and Ehsan Hassani and Roger Blanco Ribera and Hyejin Moon and Magdalena Dadela and Marco Di Lucca and Qiao Wang and Xueting Li and Jan Kautz and Simon Yuen and Umar Iqbal},
  year = {2026},
  month = {March},
  eprint = {2603.16858},
  archiveprefix = {arxiv},
}

@misc{rempe2026kimodo,
  title = {Kimodo: Scaling Controllable Human Motion Generation},
  author = {Rempe, Davis and Petrovich, Mathis and Yuan, Ye and Zhang, Haotian and Peng, Xue Bin and Jiang, Yifeng and Wang, Tingwu and Iqbal, Umar and Minor, David and de Ruyter, Michael and Li, Jiefeng and Tessler, Chen and Lim, Edy and Jeong, Eugene and Wu, Sam and Hassani, Ehsan and Huang, Michael and Yu, Jin-Bey and Chung, Chaeyeon and Song, Lina and Dionne, Olivier and Kautz, Jan and Yuen, Simon and Fidler, Sanja},
  year = {2026},
  month = {March},
  eprint = {2603.15546},
  archiveprefix = {arxiv},
}

@inproceedings{atlas2026,
  title = {Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting},
  author = {Jean Kossaifi and Nikola Kovachki and Morteza Mardani and Daniel Leibovici and Suman Ravuri and Ira Shokar and Edoardo Calvello and Mohammad Shoaib Abbas and Peter Harrington and Ashay Subramaniam and Noah Brenowitz and Boris Bonev and Wonmin Byeon and Karsten Kreis and Dale Durran and Arash Vahdat and Mike Pritchard and Jan Kautz},
  year = {2026},
  month = {January},
  booktitle = {ArXiv Preprint},
  eprint = {2601.18111},
  archiveprefix = {arxiv},
}

@inproceedings{wan2026speech,
  title = {Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception},
  author = {Zhen Wan and Chao-Han Huck Yang and Jinchuan Tian and Hanrong Ye and Ankita Pasad and Szu-Wei Fu and Arushi Goel and Ryo Hachiuma and Shizhe Diao and Kunal Dhawan and Sreyan Ghosh and Yusuke Hirota and Zhehuai Chen and Rafael Valle and Chenhui Chu and Shinji Watanabe and Boris Ginsburg and Yu-Chiang Frank Wang},
  year = {2026},
  month = {July},
  booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)},
  pages = {43124--43142},
  publisher = {Association for Computational Linguistics},
  doi = {10.18653/v1/2026.acl-long.1997},
  eprint = {2601.09413},
  archiveprefix = {arxiv},
}

@article{kovachki2024data,
  title = {Data Complexity Estimates for Operator Learning},
  author = {Kovachki, Nikola B and Lanthaler, Samuel and Mhaskar, Hrushikesh},
  year = {2026},
  journal = {Journal of Machine Learning Research},
  eprint = {2405.15992},
  archiveprefix = {arxiv},
}

@inproceedings{GSPN22025,
  title = {GSPN-2: Efficient Parallel Sequence Modeling},
  author = {Wang, Hongjun and Jiang, Yitong and McCarthy, Collin and Wehr, David and Ye, Hanrong and Li, Xinhao and Cheung, Ka Chun and Byeon, Wonmin and Gu, Jinwei and Chen, Ke and Han, Kai and Yin, Hongxu and Molchanov, Pavlo and Kautz, Jan and Liu, Sifei},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2512.07884},
  archiveprefix = {arxiv},
}

@inproceedings{fastslm2025,
  title = {Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models},
  author = {Yonggan Fu and Xin Dong and Shizhe Diao and Matthijs Van Keirsbilck and Hanrong Ye and Wonmin Byeon and Yashaswi Karnati and Lucas Liebenwein and Hannah Zhang and Nikolaus Binder and Maksim Khadkevich and Alexander Keller and Jan Kautz and Yingyan Celine Lin and Pavlo Molchanov},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  doi = {10.52202/085713-5388},
  eprint = {2511.18890},
  archiveprefix = {arxiv},
}

@inproceedings{blessing2025trust,
  title = {Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference},
  author = {Denis Blessing and Julius Berner and Lorenz Richter and Carles Domingo-Enrich and Yuanqi Du and Arash Vahdat and Gerhard Neumann},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2508.12511},
  archiveprefix = {arxiv},
}

@inproceedings{longvilar12025,
  title = {Scaling RL to Long Videos},
  author = {Chen, Yukang and Huang, Wei and Shi, Baifeng and Hu, Qinghao and Ye, Hanrong and Zhu, Ligeng and Liu, Zhijian and Molchanov, Pavlo and Kautz, Jan and Qi, Xiaojuan and Liu, Sifei and Yin, Hongxu and Lu, Yao and Han, Song},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2507.07966},
  archiveprefix = {arxiv},
}

@inproceedings{Cachay2025erdm,
  title = {Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics},
  author = {Salva R{\"u}hling Cachay and Miika Aittala and Karsten Kreis and Noah Brenowitz and Arash Vahdat and Morteza Mardani and Rose Yu},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2506.20024},
  archiveprefix = {arxiv},
}

@inproceedings{sabour2025alignyourflow,
  title = {Align Your Flow: Scaling Continuous-Time Flow Map Distillation},
  author = {Amirmojtaba Sabour and Sanja Fidler and Karsten Kreis},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2506.14603},
  archiveprefix = {arxiv},
}

@inproceedings{duisterhof2025rayst3r,
  title = {{RaySt3R}: Predicting Novel Depth Maps for Zero-Shot Object Completion},
  author = {Bardienus Pieter Duisterhof and Jan Oberst and Bowen Wen and Stan Birchfield and Deva Ramanan and Jeffrey Ichnowski},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2506.05285},
  archiveprefix = {arxiv},
}

@inproceedings{liu2025prorl,
  title = {{ProRL}: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models},
  author = {Liu, Mingjie and Diao, Shizhe and Lu, Ximing and Hu, Jian and Dong, Xin and Choi, Yejin and Kautz, Jan and Dong, Yi},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2505.24864},
  archiveprefix = {arxiv},
}

@inproceedings{Ramesh2025tts,
  title = {Test-Time Scaling of Diffusion Models via Noise Trajectory Search},
  author = {Vignav Ramesh and Morteza Mardani},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2506.03164},
  archiveprefix = {arxiv},
}

@inproceedings{chen2025eagle2.5,
  title = {Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models},
  author = {Guo Chen and Zhiqi Li and Shihao Wang and Jindong Jiang and Yicheng Liu and Lidong Lu and De-An Huang and Wonmin Byeon and Matthieu Le and Tuomas Rintamaki and Tyler Poon and Max Ehrlich and Tong Lu and Limin Wang and Bryan Catanzaro and Jan Kautz and Andrew Tao and Zhiding Yu and Guilin Liu},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2504.15271},
  archiveprefix = {arxiv},
}

@inproceedings{diao2025climb,
  title = {Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training},
  author = {Shizhe Diao and Yu Yang and Yonggan Fu and Xin Dong and Dan Su and Markus Kliegl and Zijia Chen and Peter Belcak and Yoshi Suhara and Hongxu Yin and Mostofa Patwary and Yingyan Celine Lin and Jan Kautz and Pavlo Molchanov},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2504.13161},
  archiveprefix = {arxiv},
}

@inproceedings{ssmcompression2025,
  title = {Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning},
  author = {Taghibakhshi, Ali and Sreenivas, Sharath Turuvekere and Muralidharan, Saurav and Chochowski, Marcin and Karnati, Yashaswi and Joshi, Raviraj Bhuminand and Mahabaleshwarkar, Ameya Sunil and Chen, Zijia and Suhara, Yoshi and Olabiyi, Oluwatobi and Korzekwa, Daniel and Patwary, Mostofa and Shoeybi, Mohammad and Kautz, Jan and Catanzaro, Bryan and Aithal, Ashwath and Tajbakhsh, Nima and Molchanov, Pavlo},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  doi = {10.52202/085713-4100},
  eprint = {2504.11409},
  archiveprefix = {arxiv},
}

@inproceedings{hocapwang2025,
  title = {HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction},
  author = {Jikai Wang and Qifan Zhang and Yu-Wei Chao and Bowen Wen and Xiaohu Guo and Yu Xiang},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2406.06843},
  archiveprefix = {arxiv},
}

@inproceedings{reidenbach2026atomistica,
  title = {Consistent Synthetic Sequences Unlock Structural Diversity in Fully Atomistic De Novo Protein Design},
  author = {Danny Reidenbach and Zhonglin Cao and Zuobai Zhang and Kieran Didi and Tomas Geffner and Guoqing Zhou and Jian Tang and Christian Dallago and Arash Vahdat and Emine Kucukbenli and Karsten Kreis},
  year = {2025},
  month = {December},
  booktitle = {ArXiv Preprint},
  eprint = {2512.01976},
  archiveprefix = {arxiv},
}

@article{calvello2024continuum,
  title = {Continuum Attention for Neural Operators},
  author = {Calvello, Edoardo and Kovachki, Nikola B and Levine, Matthew E and Stuart, Andrew M},
  year = {2025},
  month = {December},
  journal = {Journal of Machine Learning Research},
  volume = {26},
  eprint = {2406.06486},
  archiveprefix = {arxiv},
}

@inproceedings{TEVLM2025,
  title = {Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal},
  author = {Yitong Jiang and Jinwei Gu and Tianfan Xue and Ka Chun Cheung and Pavlo Molchanov and Hongxu Yin and Sifei Liu},
  year = {2025},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
}

@inproceedings{humanolat2025,
  title = {HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis},
  author = {Timo Teufel and Xilong Zhou and Umar Iqbal and Pramod Rao and Pulkit Gera and Jan Kautz and Vladislav Golyanik and Christian Theobalt},
  year = {2025},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2508.09137},
  archiveprefix = {arxiv},
}

@inproceedings{adahuman2025,
  title = {AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion},
  author = {Yangyi Huang and Ye Yuan and Xueting Li and Jan Kautz and Umar Iqbal},
  year = {2025},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2505.24877},
  archiveprefix = {arxiv},
}

@inproceedings{geoman2025,
  title = {GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion},
  author = {Gwanghyun Kim and Xueting Li and Ye Yuan and Koki Nagano and Tianye Li and Jan Kautz and Se Young Chun and Umar Iqbal},
  year = {2025},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2505.23085},
  archiveprefix = {arxiv},
}

@inproceedings{genmo2025,
  title = {GENMO: A GENeralist Model for Human MOtion},
  author = {Jiefeng Li and Jinkun Cao and Haotian Zhang and Davis Rempe and Jan Kautz and Umar Iqbal and Ye Yuan},
  year = {2025},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2505.01425},
  archiveprefix = {arxiv},
}

@inproceedings{hydranext2025,
  title = {Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training},
  author = {Zhenxin Li and Shihao Wang and Shiyi Lan and Zhiding Yu and Zuxuan Wu and Jose M. Alvarez},
  year = {2025},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2503.12030},
  archiveprefix = {arxiv},
}

@inproceedings{dler2026,
  title = {{DLER}: Doing Length pEnalty Right — Incentivizing More Intelligence per Token via Reinforcement Learning},
  author = {Shih-Yang Liu and Xin Dong and Ximing Lu and Shizhe Diao and Mingjie Liu and Min-Hung Chen and Hongxu Yin and Yu-Chiang Frank Wang and Kwang-Ting Cheng and Yejin Choi and Jan Kautz and Pavlo Molchanov},
  year = {2025},
  month = {October},
  booktitle = {ArXiv Preprint},
  eprint = {2510.15110},
  archiveprefix = {arxiv},
}

@inproceedings{atreya2026roboarena,
  title = {{RoboArena}: Distributed Real-World Evaluation of Generalist Robot Policies},
  author = {Pranav Atreya and Karl Pertsch and Tony Lee and Moo Jin Kim and Arhan Jain and Artur Kuramshin and Clemens Eppner and Cyrus Neary and Edward Hu and Fabio Ramos and Jonathan Tremblay and Kanav Arora and Kirsty Ellis and Luca Macesanu and Marcel Torne Villasevil and Matthew Leonard and Meedeum Cho and Ozgur Aslan and Shivin Dass and Jie Wang and William Reger and Xingfang Yuan and Xuning Yang and Abhishek Gupta and Dinesh Jayaraman and Glen Berseth and Kostas Daniilidis and Roberto Martin-Martin and Youngwoon Lee and Percy Liang and Chelsea Finn and Sergey Levine},
  year = {2025},
  month = {September},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2506.18123},
  archiveprefix = {arxiv},
}

@inproceedings{zheng2025flare,
  title = {{FLARE}: Robot Learning with Implicit World Modeling},
  author = {Ruijie Zheng and Jing Wang and Scott Reed and Johan Bjorck and Yu Fang and Fengyuan Hu and Joel Jang and Kaushil Kundalia and Zongyu Lin and Lo{\"i}c Magne and Avnish Narayan and You Liang Tan and Guanzhi Wang and Qi Wang and Jiannan Xiang and Yinzhen Xu and Seonghyeon Ye and Jan Kautz and Furong Huang and Yuke Zhu and Linxi Fan},
  year = {2025},
  month = {September},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2505.15659},
  archiveprefix = {arxiv},
}

@inproceedings{jang2025neural,
  title = {DreamGen: Unlocking Generalization in Robot Learning through Video World Models},
  author = {Joel Jang and Seonghyeon Ye and Zongyu Lin and Jiannan Xiang and Johan Bjorck and Yu Fang and Fengyuan Hu and Spencer Huang and Kaushil Kundalia and Yen-Chen Lin and Lo{\"i}c Magne and Ajay Mandlekar and Avnish Narayan and You Liang Tan and Guanzhi Wang and Jing Wang and Qi Wang and Yinzhen Xu and Xiaohui Zeng and Kaiyuan Zheng and Ruijie Zheng and Ming-Yu Liu and Luke Zettlemoyer and Dieter Fox and Jan Kautz and Scott Reed and Yuke Zhu and Linxi Fan},
  year = {2025},
  month = {September},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2505.12705},
  archiveprefix = {arxiv},
}

@article{wolf2025,
  title = {Wolf: Dense Video Captioning with a World Summarization Framework},
  author = {Boyi Li and Ligeng Zhu and Ran Tian and Shuhan Tan and Yuxiao Chen and Yao Lu and Yin Cui and Sushant Veer and Max Ehrlich and Jonah Philion and Xinshuo Weng and Fuzhao Xue and Linxi Fan and Yuke Zhu and Jan Kautz and Andrew Tao and Ming-Yu Liu and Sanja Fidler and Boris Ivanovic and Trevor Darrell and Jitendra Malik and Song Han and Marco Pavone},
  year = {2025},
  month = {September},
  journal = {Transactions on Machine Learning Research},
  eprint = {2407.18908},
  archiveprefix = {arxiv},
}

@inproceedings{shi2025lacache,
  title = {LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models},
  author = {Dachuan Shi and Yonggan Fu and Xiangchi Yuan and Zhongzhi Yu and Haoran You and Sixu Li and Xin Dong and Jan Kautz and Pavlo Molchanov and Yingyan Celine Lin},
  year = {2025},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2507.14204},
  archiveprefix = {arxiv},
}

@inproceedings{ranzinger2025featsharpvisionmodelfeatures,
  title = {FeatSharp: Your Vision Model Features, Sharper},
  author = {Mike Ranzinger and Greg Heinrich and Pavlo Molchanov and Jan Kautz and Bryan Catanzaro and Andrew Tao},
  year = {2025},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2502.16025},
  archiveprefix = {arxiv},
}

@inproceedings{lee2025genmol,
  title = {GenMol: A Drug Discovery Generalist with Discrete Diffusion},
  author = {Seul Lee and Karsten Kreis and Srimukh Prasad Veccham and Meng Liu and Danny Reidenbach and Yuxing Peng and Saee Paliwal and Weili Nie and Arash Vahdat},
  year = {2025},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2501.06158},
  archiveprefix = {arxiv},
}

@inproceedings{Puzzle2025,
  title = {Puzzle: Distillation-Based NAS for Inference-Optimized LLMs},
  author = {Akhiad Bercovich and Tomer Ronen and Talor Abramovich and Nir Ailon and Nave Assaf and Mohammad Dabbah and Ido Galil and Amnon Geifman and Yonatan Geifman and Izhak Golan and Netanel Haber and Ehud Dov Karpas and Roi Koren and Itay Levy and Pavlo Molchanov and Shahar Mor and Zach Moshe and Najeeb Nabwani and Omri Puny and Ran Rubin and Itamar Schen and Ido Shahaf and Oren Tropp and Omer Ullman Argov and Ran Zilberstein and Ran El-Yaniv},
  year = {2025},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2411.19146},
  archiveprefix = {arxiv},
}

@inproceedings{fotiadis2024stochasticflow,
  title = {Adaptive Flow Matching for Resolving Small-Scale Physics},
  author = {Stathi Fotiadis and Noah Brenowitz and Tomas Geffner and Yair Cohen and Mike Pritchard and Arash Vahdat and Morteza Mardani},
  year = {2025},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2410.19814},
  archiveprefix = {arxiv},
}

@inproceedings{maddukuri2025simandreal,
  title = {Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation},
  author = {Maddukuri, Abhiram and Jiang, Zhenyu and Chen, Lawrence Yunliang and Nasiriany, Soroush and Xie, Yuqi and Fang, Yu and Huang, Wenqi and Wang, Zu and Xu, Zhenjia and Chernyadev, Nikita and Reed, Scott and Goldberg, Ken and Mandlekar, Ajay and Fan, Linxi and Zhu, Yuke},
  year = {2025},
  month = {June},
  booktitle = {Robotics: Science and Systems (RSS)},
  eprint = {2503.24361},
  archiveprefix = {arxiv},
}

@inproceedings{he2025asap,
  title = {ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills},
  author = {He, Tairan and Gao, Jiawei and Xiao, Wenli and Zhang, Yuanhang and Wang, Zi and Wang, Jiashun and Luo, Zhengyi and He, Guanqi and Sobanbabu, Nikhil and Pan, Chaoyi and Yi, Zeji and Qu, Guannan and Kitani, Kris and Hodgins, Jessica and Fan, Linxi and Zhu, Yuke and Liu, Changliu and Shi, Guanya},
  year = {2025},
  month = {June},
  booktitle = {Robotics: Science and Systems (RSS)},
  eprint = {2502.01143},
  archiveprefix = {arxiv},
}

@inproceedings{navila2024,
  title = {NaVILA: Legged Robot Vision-Language-Action Model for Navigation},
  author = {An-Chieh Cheng and Yandong Ji and Zhaojing Yang and Zaitian Gongye and Xueyan Zou and Jan Kautz and Erdem Biyik and Hongxu Yin and Sifei Liu and Xiaolong Wang},
  year = {2025},
  month = {June},
  booktitle = {Robotics: Science and Systems (RSS)},
  eprint = {2412.04453},
  archiveprefix = {arxiv},
}

@inproceedings{argus2025,
  title = {Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought},
  author = {Yunze Man and De-An Huang and Guilin Liu and Shiwei Sheng and Shilong Liu and Liangyan Gui and Jan Kautz and Yu-Xiong Wang and Zhiding Yu},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2505.23766},
  archiveprefix = {arxiv},
}

@inproceedings{tomandjerry2025,
  title = {One-Minute Video Generation with Test-Time Training},
  author = {Karan Dalal and Daniel Koceja and Jiarui Xu and Yue Zhao and Shihao Han and Ka Chun Cheung and Jan Kautz and Yejin Choi and Yu Sun and Xiaolong Wang},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2504.05298},
  archiveprefix = {arxiv},
}

@inproceedings{scaling4k2025,
  title = {Scaling Vision Pre-Training to 4K Resolution},
  author = {Baifeng Shi and Boyi Li and Han Cai and Yao Lu and Sifei Liu and Marco Pavone and Jan Kautz and Song Han and Trevor Darrell and Pavlo Molchanov and Hongxu Yin},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2503.19903},
  archiveprefix = {arxiv},
}

@inproceedings{choy2025mosaic,
  title = {{Mosaic3D}: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation},
  author = {Junha Lee and Chunghyun Park and Jaesung Choe and Yu-Chiang Frank Wang and Jan Kautz and Minsu Cho and Chris Choy},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2502.02548},
  archiveprefix = {arxiv},
}

@inproceedings{gspn2025,
  title = {Parallel Sequence Modeling via Generalized Spatial Propagation Network},
  author = {Hongjun Wang and Wonmin Byeon and Jiarui Xu and Jinwei Gu and Ka Chun Cheung and Xiaolong Wang and Kai Han and Jan Kautz and Sifei Liu},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2501.12381},
  archiveprefix = {arxiv},
}

@inproceedings{liang2025zeroSF,
  title = {Zero-Shot Monocular Scene Flow Estimation in the Wild},
  author = {Yiqing Liang and Abhishek Badki and Hang Su and James Tompkin and Orazio Gallo},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2501.10357},
  archiveprefix = {arxiv},
}

@inproceedings{stereoanything2025,
  title = {FoundationStereo: Zero-Shot Stereo Matching},
  author = {Bowen Wen and Matthew Trepte and Oluwaseun Joseph Aribido and Jan Kautz and Orazio Gallo and Stan Birchfield},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2501.09898},
  archiveprefix = {arxiv},
}

@inproceedings{omnirgpt2025,
  title = {Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks},
  author = {Miran Heo and Min-Hung Chen and De-An Huang and Sifei Liu and Subhashree Radhakrishnan and Seon Joo Kim and Yu-Chiang Frank Wang and Ryo Hachiuma},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2501.08326},
  archiveprefix = {arxiv},
}

@inproceedings{blobgenvid2025,
  title = {BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations},
  author = {Weixi Feng and Chao Liu and Sifei Liu and William Yang Wang and Arash Vahdat and Weili Nie},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2501.07647},
  archiveprefix = {arxiv},
}

@inproceedings{li2025simavatar,
  title = {SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing},
  author = {Xueting Li and Ye Yuan and Shalini De Mello and Gilles Daviet and Jonathan Leaf and Miles Macklin and Jan Kautz and Umar Iqbal},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2412.09545},
  archiveprefix = {arxiv},
}

@inproceedings{radioamp2025,
  title = {{RADIOv2.5}: Improved Baselines for Agglomerative Vision Foundation Models},
  author = {Greg Heinrich and Mike Ranzinger and Hongxu Yin and Yao Lu and Jan Kautz and Bryan Catanzaro and Andrew Tao and Pavlo Molchanov},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2412.07679},
  archiveprefix = {arxiv},
}

@inproceedings{nvila2025,
  title = {NVILA: Efficient Frontier Visual Language Models},
  author = {Zhijian Liu and Ligeng Zhu and Baifeng Shi and Zhuoyang Zhang and Yuming Lou and Shang Yang and Haocheng Xi and Shiyi Cao and Yuxian Gu and Dacheng Li and Xiuyu Li and Haotian Tang and Yunhao Fang and Yukang Chen and Cheng-Yu Hsieh and De-An Huang and An-Chieh Cheng and Jinyi Hu and Sifei Liu and Ranjay Krishna and Pavlo Molchanov and Jan Kautz and Hongxu Yin and Song Han and Yao Lu},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2412.04468},
  archiveprefix = {arxiv},
}

@inproceedings{robospatial2025,
  title = {{RoboSpatial}: Teaching Spatial Understanding to {2D} and {3D} Vision-Language Models for Robotics},
  author = {Chan Hee Song and Valts Blukis and Jonathan Tremblay and Stephen Tyree and Yu Su and Stan Birchfield},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2411.16537},
  archiveprefix = {arxiv},
}

@inproceedings{hatamizadeh2025mamba,
  title = {{MambaVision}: A Hybrid Mamba-Transformer Vision Backbone},
  author = {Ali Hatamizadeh and Jan Kautz},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2407.08083},
  archiveprefix = {arxiv},
}

@inproceedings{mvp3d2025,
  title = {{3D-MVP}: 3D Multiview Pretraining for Manipulation},
  author = {Shengyi Qian and Kaichun Mo and Valts Blukis and David Fouhey and Dieter Fox and Ankit Goyal},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2406.18158},
  archiveprefix = {arxiv},
}

@inproceedings{wang2024omnidrive,
  title = {{OmniDrive}: A Holistic Vision-Language Dataset for Autonomous Driving with Counter Factual Reasoning},
  author = {Shihao Wang and Zhiding Yu and Xiaohui Jiang and Shiyi Lan and Min Shi and Nadine Chang and Jan Kautz and Ying Li and Jose M. Alvarez},
  year = {2025},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2405.01533},
  archiveprefix = {arxiv},
}

@article{zheng2024ensemble,
  title = {Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems},
  author = {Hongkai Zheng and Wenda Chu and Austin Wang and Nikola Kovachki and Ricardo Baptista and Yisong Yue},
  year = {2025},
  month = {June},
  journal = {Transactions on Machine Learning Research},
  eprint = {2409.20175},
  archiveprefix = {arxiv},
}

@inproceedings{belcak2025small,
  title = {Small Language Models are the Future of Agentic AI},
  author = {Peter Belcak and Greg Heinrich and Shizhe Diao and Yonggan Fu and Xin Dong and Saurav Muralidharan and Yingyan Celine Lin and Pavlo Molchanov},
  year = {2025},
  month = {June},
  booktitle = {ArXiv Preprint},
  eprint = {2506.02153},
  archiveprefix = {arxiv},
}

@inproceedings{jawale2025objecttransport,
  title = {Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning},
  author = {Neel Anand Jawale and Byron Boots and Balakumar Sundaralingam and Mohak Bhardwaj},
  year = {2025},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2412.00086},
  archiveprefix = {arxiv},
}

@inproceedings{wang2025policysteering,
  title = {Inference-Time Policy Steering Through Human Interactions},
  author = {Yanwei Wang and Lirui Wang and Yilun Du and Balakumar Sundaralingam and Xuning Yang and Yu-Wei Chao and Claudia Pérez-D'Arpino and Dieter Fox and Julie A. Shah},
  year = {2025},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  doi = {10.1109/ICRA55743.2025.11127931},
  eprint = {2411.16627},
  archiveprefix = {arxiv},
}

@inproceedings{hsu2025spot,
  title = {{SPOT}: {SE(3)} Pose Trajectory Diffusion for Object-Centric Manipulation},
  author = {Cheng-Chun Hsu and Bowen Wen and Jie Xu and Yashraj Narang and Xiaolong Wang and Yuke Zhu and Joydeep Biswas and Stan Birchfield},
  year = {2025},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2411.00965},
  archiveprefix = {arxiv},
}

@inproceedings{he2025hover,
  title = {{HOVER}: {V}ersatile Neural Whole-Body Controller for Humanoid Robots},
  author = {Tairan He and Wenli Xiao and Toru Lin and Zhengyi Luo and Zhenjia Xu and Zhenyu Jiang and Jan Kautz and Changliu Liu and Guanya Shi and Xiaolong Wang and Linxi Fan and Yuke Zhu},
  year = {2025},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2410.21229},
  archiveprefix = {arxiv},
}

@article{aimnshoot2025,
  title = {Modeling Visually-Guided Aim-and-Shoot Behavior in First-Person Shooters},
  author = {June-Seop Yoon and Hee-Seung Moon and Ben Boudaoud and Josef Spjut and Iuri Frosio and Byungjoo Lee and Joohwan Kim},
  year = {2025},
  month = {May},
  journal = {International Journal of Human-Computer Studies},
  volume = {199},
  doi = {10.1016/j.ijhcs.2025.103503},
}

@inproceedings{ye2024longmamba,
  title = {LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement},
  author = {Zhifan Ye and Kejing Xia and Yonggan Fu and Xin Dong and Jihoon Hong and Xiangchi Yuan and Shizhe Diao and Jan Kautz and Pavlo Molchanov and Yingyan (Celine) Lin},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2504.16053},
  archiveprefix = {arxiv},
}

@inproceedings{cai2024llamaflex,
  title = {LlamaFlex: Many-in-One LLMs via Generalized Pruning and Weight Sharing},
  author = {Ruisi Cai and Saurav Muralidharan and Hongxu Yin and Zhangyang Wang and Jan Kautz and Pavlo Molchanov},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
}

@inproceedings{zheng2024inversebench,
  title = {InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences},
  author = {Hongkai Zheng and Wenda Chu and Bingliang Zhang and Zihui Wu and Austin Wang and Berthy Feng and Caifeng Zou and Yu Sun and Nikola Kovachki and Zachary E Ross and Katherine Bouman and Yisong Yue},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2503.11043},
  archiveprefix = {arxiv},
}

@inproceedings{stark2024protcomposer,
  title = {ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids},
  author = {Hannes Stark and Bowen Jing and Tomas Geffner and Jason Yim and Tommi Jaakkola and Arash Vahdat and Karsten Kreis},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2503.05025},
  archiveprefix = {arxiv},
}

@inproceedings{geffner2024pfm,
  title = {Proteina: Scaling Flow-based Protein Structure Generative Models},
  author = {Tomas Geffner and Kieran Didi and Zuobai Zhang and Danny Reidenbach and Zhonglin Cao and Jason Yim and Mario Geiger and Christian Dallago and Emine Kucukbenli and Arash Vahdat and Karsten Kreis},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2503.00710},
  archiveprefix = {arxiv},
}

@inproceedings{hui2025nso,
  title = {Not-So-Optimal Transport Flows for 3D Point Cloud Generation},
  author = {Ka-Hei Hui and Chao Liu and Xiaohui Zeng and Chi-Wing Fu and Arash Vahdat},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2502.12456},
  archiveprefix = {arxiv},
}

@inproceedings{yanggated2024,
  title = {Gated Delta Networks: Improving Mamba2 with Delta Rule},
  author = {Songlin Yang and Jan Kautz and Ali Hatamizadeh},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2412.06464},
  archiveprefix = {arxiv},
}

@inproceedings{xind2025hymba,
  title = {Hymba: A Hybrid-head Architecture for Small Language Models},
  author = {Xin Dong and Yonggan Fu and Shizhe Diao and Wonmin Byeon and Zijia Chen and Ameya Sunil Mahabaleshwarkar and Shih-Yang Liu and Matthijs Van Keirsbilck and Min-Hung Chen and Yoshi Suhara and Yingyan Celine Lin and Jan Kautz and Pavlo Molchanov},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2411.13676},
  archiveprefix = {arxiv},
}

@inproceedings{xu2024eddm,
  title = {Energy-based Diffusion Language Models for Text Generation},
  author = {Minkai Xu and Tomas Geffner and Karsten Kreis and Weili Nie and Yilun Xu and Jure Leskovec and Stefano Ermon and Arash Vahdat},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2410.21357},
  archiveprefix = {arxiv},
}

@inproceedings{lee2024tcm,
  title = {Truncated Consistency Models},
  author = {Sangyun Lee and Yilun Xu and Tomas Geffner and Giulia Fanti and Karsten Kreis and Arash Vahdat and Weili Nie},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2410.14895},
  archiveprefix = {arxiv},
}

@inproceedings{pandey2024heavytailed,
  title = {Heavy-Tailed Diffusion Models},
  author = {Kushagra Pandey and Jaideep Pathak and Yilun Xu and Stephan Mandt and Mike Pritchard and Arash Vahdat and Morteza Mardani},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2410.14171},
  archiveprefix = {arxiv},
}

@inproceedings{liu2025think,
  title = {Think while You Generate: Discrete Diffusion with Planned Denoising},
  author = {Sulin Liu and Juno Nam and Andrew Campbell and Hannes Stark and Yilun Xu and Tommi Jaakkola and Rafael Gomez-Bombarelli},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2410.06264},
  archiveprefix = {arxiv},
}

@inproceedings{eulerflow2025,
  title = {Neural Eulerian Scene Flow Fields},
  author = {Kyle Vedder and Neehar Peri and Ishan Khatri and Siyi Li and Eric Eaton and Mehmet Kemal Kocamaz and Yue Wang and Zhiding Yu and Deva Ramanan and Joachim Pehserl},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2410.02031},
  archiveprefix = {arxiv},
}

@inproceedings{wu2025vilau,
  title = {VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation},
  author = {Yecheng Wu and Zhuoyang Zhang and Junyu Chen and Haotian Tang and Dacheng Li and Yunhao Fang and Ligeng Zhu and Enze Xie and Hongxu Yin and Li Yi and Song Han and Yao Lu},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2409.04429},
  archiveprefix = {arxiv},
}

@inproceedings{eagle2025,
  title = {Eagle: Exploring The Design Space for Multimodal {LLMs} with Mixture of Encoders},
  author = {Min Shi and Fuxiao Liu and Shihao Wang and Shijia Liao and Subhashree Radhakrishnan and Yilin Zhao and De-An Huang and Hongxu Yin and Karan Sapra and Yaser Yacoob and Humphrey Shi and Bryan Catanzaro and Andrew Tao and Jan Kautz and Zhiding Yu and Guilin Liu},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2408.15998},
  archiveprefix = {arxiv},
}

@inproceedings{chen25longvila,
  title = {{LongVILA}: Scaling Long-Context Visual Language Models for Long Videos},
  author = {Yukang Chen and Fuzhao Xue and Dacheng Li and Qinghao Hu and Ligeng Zhu and Xiuyu Li and Yunhao Fang and Haotian Tang and Shang Yang and Zhijian Liu and Yihui He and Hongxu Yin and Pavlo Molchanov and Jan Kautz and Linxi Fan and Yuke Zhu and Yao Lu and Song Han},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2408.10188},
  archiveprefix = {arxiv},
}

@inproceedings{repulsive2025,
  title = {Repulsive Latent Score Distillation for Solving Inverse Problems},
  author = {Nicolas Zilberstein and Morteza Mardani and Santiago Segarra},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2406.16683},
  archiveprefix = {arxiv},
}

@inproceedings{t-stitch2024,
  title = {{T-Stitch}: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching},
  author = {Zizheng Pan and Bohan Zhuang and De-An Huang and Weili Nie and Zhiding Yu and Chaowei Xiao and Jianfei Cai and Anima Anandkumar},
  year = {2025},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2402.14167},
  archiveprefix = {arxiv},
}

@inproceedings{snapit2024,
  title = {Snap-it, Tap-it, Splat-it: {T}actile-Informed {3D} Gaussian Splatting for Reconstructing Challenging Surfaces},
  author = {Mauro Comi and Alessio Tonioni and Max Yang and Jonathan Tremblay and Valts Blukis and Yijiong Lin and Nathan F. Lepora and Laurence Aitchison},
  year = {2025},
  month = {March},
  booktitle = {International Conference on 3D Vision (3DV)},
  eprint = {2403.20275},
  archiveprefix = {arxiv},
}

@inproceedings{gr00tn1_2025,
  title = {{GR00T} {N1}: An Open Foundation Model for Generalist Humanoid Robots},
  author = {{NVIDIA} and Johan Bjorck and Fernando Castañeda and Nikita Cherniadev and Xingye Da and Runyu Ding and Linxi "Jim" Fan and Yu Fang and Dieter Fox and Fengyuan Hu and Spencer Huang and Joel Jang and Zhenyu Jiang and Jan Kautz and Kaushil Kundalia and Lawrence Lao and Zhiqi Li and Zongyu Lin and Kevin Lin and Guilin Liu and Edith Llontop and Loic Magne and Ajay Mandlekar and Avnish Narayan and Soroush Nasiriany and Scott Reed and You Liang Tan and Guanzhi Wang and Zu Wang and Jing Wang and Qi Wang and Jiannan Xiang and Yuqi Xie and Yinzhen Xu and Zhenjia Xu and Seonghyeon Ye and Zhiding Yu and Ao Zhang and Hao Zhang and Yizhou Zhao and Ruijie Zheng and Yuke Zhu},
  year = {2025},
  month = {March},
  booktitle = {ArXiv Preprint},
  eprint = {2503.14734},
  archiveprefix = {arxiv},
}

@inproceedings{sun2024enhancedsaliency,
  title = {Advancing Weight and Channel Sparsification with Enhanced Saliency},
  author = {Xinglong Sun and Maying Shen and Hongxu Yin and Lei Mao and Pavlo Molchanov and Jose M. Alvarez},
  year = {2025},
  month = {February},
  booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
  eprint = {2502.03658},
  archiveprefix = {arxiv},
}

@inproceedings{ganj2025hybriddepth,
  title = {{HybridDepth}: {R}obust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors},
  author = {Ashkan Ganj and Hang Su and Tian Guo},
  year = {2025},
  month = {February},
  booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
  eprint = {2407.18443},
  archiveprefix = {arxiv},
}

@article{mardani2025kmscale,
  title = {Residual corrective diffusion modeling for km-scale atmospheric downscaling},
  author = {Morteza Mardani and Noah Brenowitz and Yair Cohen and Jaideep Pathak and Chieh-Yu Chen and Cheng-Chin Liu and Arash Vahdat and Mohammad Amin Nabian and Tao Ge and Akshay Subramaniam and Karthik Kashinath and Jan Kautz and Mike Pritchard},
  year = {2025},
  month = {February},
  journal = {Nature Communications Earth & Environment},
  volume = {6},
  number = {124},
  eprint = {2309.15214},
  archiveprefix = {arxiv},
}

@article{law2024directed,
  title = {Directed Graph Generation with Heat Kernels},
  author = {Marc T. Law and Karsten Kreis and Haggai Maron},
  year = {2025},
  month = {January},
  journal = {Transactions on Machine Learning Research},
}

@article{lim2025score,
  title = {Score-Based Diffusion Models in Function Space},
  author = {Jae Hyun Lim and Nikola B. Kovachki and Ricardo Baptista and Christopher Beckham and Kamyar Azizzadenesheli and Jean Kossaifi and Vikram Voleti and Jiaming Song and Karsten Kreis and Jan Kautz and Christopher Pal and Arash Vahdat and Anima Anandkumar},
  year = {2025},
  journal = {Journal of Machine Learning Research},
  volume = {26},
  number = {158},
  pages = {1--62},
  eprint = {2302.07400},
  archiveprefix = {arxiv},
}

@article{kossaifi2024library,
  title = {A Library for Learning Neural Operators},
  author = {Kossaifi, Jean and Kovachki, Nikola and Li, Zongyi and Pitt, David and Liu-Schiaffini, Miguel and George, Robert Joseph and Bonev, Boris and Azizzadenesheli, Kamyar and Berner, Julius and Duruisseaux, Valentin and Anandkumar, Anima},
  year = {2024},
  month = {December},
  journal = {ArXiv Preprint},
  eprint = {2412.10354},
  archiveprefix = {arxiv},
}

@inproceedings{liu2024cosine,
  title = {{CosAE}: Learnable Fourier Series for Image Restoration},
  author = {Sifei Liu and Shalini De Mello and Jan Kautz},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
}

@inproceedings{lee2024frag,
  title = {Molecule Generation with Fragment Retrieval Augmentation},
  author = {Seul Lee and Karsten Kreis and Srimukh Prasad Veccham and Meng Liu and Danny Reidenbach and Saee Paliwal and Arash Vahdat and Weili Nie},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2411.12078},
  archiveprefix = {arxiv},
}

@inproceedings{daras2024warpeddiff,
  title = {Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models},
  author = {Giannis Daras and Weili Nie and Karsten Kreis and Alex Dimakis and Morteza Mardani and Nikola Kovachki and Arash Vahdat},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2410.16152},
  archiveprefix = {arxiv},
}

@inproceedings{factorsim2024,
  title = {{FACTORSIM}: Generative Simulation via Factorized Representation},
  author = {Fan-Yun Sun and Harini S I and Angela Yi and Yihan Zhou and Alex Zook and Jonathan Tremblay and Logan Cross and Jiajun Wu and Nick Haber},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2409.17652},
  archiveprefix = {arxiv},
}

@inproceedings{ampere2024,
  title = {MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models},
  author = {Gongfan Fang and Hongxu Yin and Saurav Muralidharan and Greg Heinrich and Jeff Pool and Jan Kautz and  Pavlo Molchanov and Xinchao Wang},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2409.17481},
  archiveprefix = {arxiv},
}

@inproceedings{minitron2024,
  title = {Compact Language Models via Pruning and Knowledge Distillation},
  author = {Saurav Muralidharan and Sharath Turuvekere Sreenivas and Raviraj Joshi and Marcin Chochowski and Mostofa Patwary and Mohammad Shoeybi and Bryan Catanzaro and Jan Kautz and Pavlo Molchanov},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2407.14679},
  archiveprefix = {arxiv},
}

@inproceedings{gu2024alidiff,
  title = {Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization},
  author = {Siyi Gu and Minkai Xu and Alexander S Powers and Weili Nie and Tomas Geffner and Karsten Kreis and Jure Leskovec and Arash Vahdat and Stefano Ermon},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2407.01648},
  archiveprefix = {arxiv},
}

@inproceedings{ren2024l4gm,
  title = {{L4GM}: Large 4D Gaussian Reconstruction Model},
  author = {Jiawei Ren and Kevin Xie and Ashkan Mirzaei and Hanxue Liang and Xiaohui Zeng and Karsten Kreis and Ziwei Liu and Antonio Torralba and Sanja Fidler and Seung Wook Kim and Huan Ling},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2406.10324},
  archiveprefix = {arxiv},
}

@inproceedings{cheng2024spatialrgpt,
  title = {{SpatialRGPT}: Grounded Spatial Reasoning in Vision-Language Models},
  author = {An-Chieh Cheng and Hongxu Yin and Yang Fu and Qiushan Guo and Ruihan Yang and Jan Kautz and Xiaolong Wang and Sifei Liu},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2406.01584},
  archiveprefix = {arxiv},
}

@inproceedings{3dgm2024,
  title = {Memorize What Matters: Emergent Scene Decomposition from Multitraverse},
  author = {Yiming Li and Zehong Wang and Yue Wang and Zhiding Yu and Zan Gojcic and Marco Pavone and Chen Feng and Jose M. Alvarez},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2405.17187},
  archiveprefix = {arxiv},
}

@inproceedings{pan2024lisa,
  title = {LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning},
  author = {Pan, Rui and Liu, Xiang and Diao, Shizhe and Pi, Renjie and Zhang, Jipeng and Han, Chi and Zhang, Tong},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2403.17919},
  archiveprefix = {arxiv},
}

@inproceedings{rahman2024pretraining,
  title = {Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs},
  author = {Md Ashiqur Rahman and Robert Joseph George and Mogab Elleithy and Daniel Leibovici and Zongyi Li and Boris Bonev and Colin White and Julius Berner and Raymond A Yeh and Jean Kossaifi and Kamyar Azizzadenesheli and Anima Anandkumar},
  year = {2024},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2403.12553},
  archiveprefix = {arxiv},
}

@article{blob3dgen2024,
  title = {{BlobGEN-3D}: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs},
  author = {Chao Liu and Weili Nie and Sifei Liu and Abhishek Badki and Hang Su and Morteza Mardani and Benjamin Eckart and Arash Vahdat},
  year = {2024},
  month = {December},
  journal = {ACM Transactions on Graphics (SIGGRAPH ASIA)},
  doi = {10.1145/3680528.3687645},
}

@article{diffuhaul2024,
  title = {DiffUHaul: A Training-Free Method for Object Dragging in Images},
  author = {Omri Avrahami and Rinon Gal and Gal Chechik and Ohad Fried and Dani Lischinski and Arash Vahdat and Weili Nie},
  year = {2024},
  month = {December},
  journal = {ACM Transactions on Graphics (SIGGRAPH ASIA)},
  eprint = {2406.01594},
  archiveprefix = {arxiv},
}

@inproceedings{liu2024streamchat,
  title = {StreamChat: Chatting with Streaming Video},
  author = {Jihao Liu and Zhiding Yu and Shiyi Lan and Shihao Wang and Rongyao Fang and Jan Kautz and Hongsheng Li and Jose M. Alvarez},
  year = {2024},
  month = {December},
  booktitle = {ArXiv Preprint},
  eprint = {2412.08646},
  archiveprefix = {arxiv},
}

@inproceedings{avoideverything2024,
  title = {Avoid Everything: Model-Free Collision Avoidance with Expert-Guided Fine-Tuning},
  author = {Adam Fishman and Aaron Walsman and Mohak Bhardwaj and Wentao Yuan and Balakumar Sundaralingam and Byron Boots and Dieter Fox},
  year = {2024},
  month = {November},
  booktitle = {Conference on Robot Learning (CoRL)},
}

@inproceedings{skillgen2024,
  title = {SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment},
  author = {Caelan Reed Garrett and Ajay Mandlekar and Bowen Wen and Dieter Fox},
  year = {2024},
  month = {November},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2410.18907},
  archiveprefix = {arxiv},
}

@inproceedings{diffseeder2024,
  title = {DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning},
  author = {Huang Huang and Balakumar Sundaralingam and Arsalan Mousavian and Adithyavairavan Murali and Ken Goldberg and Dieter Fox},
  year = {2024},
  month = {November},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2410.16727},
  archiveprefix = {arxiv},
}

@inproceedings{harmon2024,
  title = {Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions},
  author = {Zhenyu Jiang and Yuqi Xie and Jinhan Li and Ye Yuan and Yifeng Zhu and Yuke Zhu},
  year = {2024},
  month = {November},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2410.12773},
  archiveprefix = {arxiv},
}

@inproceedings{robopoint2024,
  title = {{RoboPoint}: A Vision-Language Model for Spatial Affordance Prediction for Robotics},
  author = {Wentao Yuan and Jiafei Duan and Valts Blukis and Wilbert Pumacay and Ranjay Krishna and Adithyavairavan Murali and Arsalan Mousavian and Dieter Fox},
  year = {2024},
  month = {November},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2406.10721},
  archiveprefix = {arxiv},
}

@article{Frontiers_Kamyar_2024,
  title = {Promoting best practices in ocean forecasting through an Operational Readiness Level},
  author = {Alvarez Fanjul, E.  and Ciliberti, S.  and Pearlman, J.  and Wilmer-Becker, K. and Bahurel, P.    and Ardhuin, F.  and Arnaud, A.  and Azizzadenesheli, K. and Others, Others},
  year = {2024},
  month = {November},
  journal = {Frontiers in Marine Science},
  doi = {10.3389/fmars.2024.1443284},
}

@inproceedings{li2024sscbench,
  title = {{SSCBench}: {A} Large-Scale {3D} Semantic Scene Completion Benchmark for Autonomous Driving},
  author = {Yiming Li and Sihang Li and Xinhao Liu and Moonjun Gong and Kenan Li and Nuo Chen and Zijun Wang and Zhiheng Li and Tao Jiang and Fisher Yu and Yue Wang and Hang Zhao and Zhiding Yu and Chen Feng},
  year = {2024},
  month = {October},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  eprint = {2306.09001},
  archiveprefix = {arxiv},
}

@inproceedings{deformgs2024,
  title = {{DeformGS}: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation},
  author = {Bardienus P. Duisterhof and Mandi Zhao and Yunchao Yao and Jia-Wei Liu and Jenny Seidenschwarz and Mike Zheng Shou and Deva Ramanan and Shuran Song and Stan Birchfield and Bowen Wen and Jeffrey Ichnowski},
  year = {2024},
  month = {October},
  booktitle = {Workshop on the Algorithmic Foundations of Robotics (WAFR)},
  eprint = {2312.00583},
  archiveprefix = {arxiv},
}

@inproceedings{li2024coin,
  title = {{COIN}: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation},
  author = {Jiefeng Li and Ye Yuan and Davis Rempe and Haotian Zhang and Pavlo Molchanov and Cewu Lu and Jan Kautz and Umar Iqbal},
  year = {2024},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2408.16426},
  archiveprefix = {arxiv},
}

@inproceedings{huang2024lita,
  title = {{LITA}: {L}anguage Instructed Temporal-localization Assistant},
  author = {De-An Huang and Shijia Liao and Subhashree Radhakrishnan and Hongxu Yin and Pavlo Molchanov and Zhiding Yu and Jan Kautz},
  year = {2024},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2403.19046},
  archiveprefix = {arxiv},
}

@inproceedings{prolab2024,
  title = {A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties},
  author = {Junfei Xiao and Ziqi Zhou and Wenxuan Li and Shiyi Lan and Jieru Mei and Zhiding Yu and Bingchen Zhao and Alan Yuille and Yuyin Zhou and Cihang Xie},
  year = {2024},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2312.13764},
  archiveprefix = {arxiv},
}

@inproceedings{oh2024mevg,
  title = {MEVG: Multi-event Video Generation with Text-to-Video Models},
  author = {Gyeongrok Oh and Jaehwan Jeong and Sieun Kim and Wonmin Byeon and Jinkyu Kim and Sungwoong Kim and Sangpil Kim},
  year = {2024},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2312.04086},
  archiveprefix = {arxiv},
}

@inproceedings{Hatamizadeh2024diffit,
  title = {{DiffiT}: {D}iffusion Vision Transformers for Image Generation},
  author = {Ali Hatamizadeh and Jiaming Song and Guilin Liu and Jan Kautz and Arash Vahdat},
  year = {2024},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2312.02139},
  archiveprefix = {arxiv},
}

@inproceedings{prashnani2023avatar,
  title = {Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos},
  author = {Ekta Prashnani and Koki Nagano and Shalini De Mello and David Luebke and Orazio Gallo},
  year = {2024},
  month = {September},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2305.03713},
  archiveprefix = {arxiv},
}

@article{xu2024agg,
  title = {{AGG}: {A}mortized Generative {3D} {G}aussians for Single Image to {3D}},
  author = {Dejia Xu and Ye Yuan and Morteza Mardani and Sifei Liu and Jiaming Song and Zhangyang Wang and Arash Vahdat},
  year = {2024},
  month = {October},
  journal = {Transactions on Machine Learning Research},
  eprint = {2401.04099},
  archiveprefix = {arxiv},
}

@article{shi2024universal,
  title = {Universal Functional Regression with Neural Operator Flows},
  author = {Shi, Yaozhong and Gao, Angela F and Ross, Zachary E and Azizzadenesheli, Kamyar},
  year = {2024},
  month = {October},
  journal = {Transactions on Machine Learning Research},
  eprint = {2404.02986},
  archiveprefix = {arxiv},
}

@article{Zou2024,
  title = {Deep Neural Helmholtz Operators for 3D Elastic Wave Propagation and Inversion},
  author = {Caifeng Zou and Kamyar Azizzadenesheli and Zachary E. Ross and Robert W. Clayton},
  year = {2024},
  month = {September},
  journal = {Geophysical Journal International},
  eprint = {2311.09608},
  archiveprefix = {arxiv},
}

@article{ma2024calibrated,
  title = {Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction},
  author = {Ma, Ziqi and Pitt, David and Azizzadenesheli, Kamyar and Anandkumar, Anima},
  year = {2024},
  month = {August},
  journal = {Transactions on Machine Learning Research},
}

@article{laleFALCON2024,
  title = {FALCON: Fourier Adaptive Learning and Control for Disturbance Rejection Under Extreme Turbulence},
  author = {Sahin Lale and Peter I. Renn and Kamyar Azizzadenesheli and Babak Hassibi and Morteza Gharib and Anima Anandkumar},
  year = {2024},
  month = {September},
  journal = {npj Robotics},
  doi = {10.1038/s44182-024-00013-0},
}

@article{george2024incremental,
  title = {Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs},
  author = {George, Robert Joseph and Zhao, Jiawei and Kossaifi, Jean and Li, Zongyi and Anandkumar, Anima},
  year = {2024},
  month = {September},
  journal = {Transactions on Machine Learning Research},
  eprint = {2211.15188},
  archiveprefix = {arxiv},
}

@inproceedings{durst2024csgo,
  title = {Learning to Move Like Professional Counter-Strike Players},
  author = {David Durst and Feng Xie and Vishnu Sarukkai and Brennan Shacklett and Iuri Frosio and Chen Tessler and Joohwan Kim and Carly Taylor and Gilbert Bernstein and Sanjiban Choudhury and Pat Hanrahan and Kayvon Fatahalian},
  year = {2024},
  month = {August},
  booktitle = {ACM SIGGRAPH / Eurographics Symposium on Computer Animation},
  eprint = {2408.13934},
  archiveprefix = {arxiv},
}

@article{bhattacharya2024learning,
  title = {Learning Homogenization For Elliptic Operators},
  author = {Bhattacharya, Kaushik and Kovachki, Nikola and Rajan, Aakila and Stuart, Andrew M and Trautner, Margaret},
  year = {2024},
  month = {January},
  journal = {SIAM Journal on Numerical Analysis},
  eprint = {2306.12006},
  archiveprefix = {arxiv},
}

@article{lee2024lisa,
  title = {{LISA}: {L}ocalized Image Stylization with Audio via Implicit Neural Representation},
  author = {Seung Hyun Lee and Chanyoung Kim and Wonmin Byeon and Sang Ho Yoon and Jinkyu Kim and Sangpil Kim},
  year = {2024},
  month = {August},
  journal = {Computational Visual Media},
  eprint = {2211.11381},
  archiveprefix = {arxiv},
}

@article{kossaifi2023multi,
  title = {Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs},
  author = {Jean Kossaifi and Nikola Kovachki and Kamyar Azizzadenesheli and Anima Anandkumar},
  year = {2024},
  month = {August},
  journal = {Transactions on Machine Learning Research},
  eprint = {2310.00120},
  archiveprefix = {arxiv},
}

@inproceedings{xu2024discodiff,
  title = {{DisCo-Diff}: {E}nhancing Continuous Diffusion Models with Discrete Latents},
  author = {Xu, Yilun and Corso, Gabriele and Jaakkola, Tommi and Vahdat, Arash and Kreis, Karsten},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2407.03300},
  archiveprefix = {arxiv},
}

@inproceedings{cai2024flextron,
  title = {{Flextron}: {M}any-in-One Flexible Large Language Model},
  author = {Ruisi Cai and Saurav Muralidharan and Greg Heinrich and Hongxu Yin and Zhangyang Wang and Jan Kautz, and Pavlo Molchanov},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2406.10260},
  archiveprefix = {arxiv},
}

@inproceedings{Nie2024compositional,
  title = {Compositional Text-to-Image Generation with Dense Blob Representations},
  author = {Weili Nie and Sifei Liu and Morteza Mardani and Chao Liu and Benjamin Eckart and Arash Vahdat},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2405.08246},
  archiveprefix = {arxiv},
}

@inproceedings{Sabour2024alignsteps,
  title = {Align Your Steps: Optimizing Sampling Schedules in Diffusion Models},
  author = {Amirmojtaba Sabour and Sanja Fidler and Karsten Kreis},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2404.14507},
  archiveprefix = {arxiv},
}

@inproceedings{liu2024neural,
  title = {Neural Operators with Localized Integral and Differential Kernels},
  author = {Liu-Schiaffini, Miguel and Berner, Julius and Bonev, Boris and Kurth, Thorsten and Azizzadenesheli, Kamyar and Anandkumar, Anima},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2402.16845},
  archiveprefix = {arxiv},
}

@inproceedings{liu2024dora,
  title = {{DoRA}: {W}eight-decomposed Low-rank Adaptation},
  author = {Shih-Yang Liu and Chien-yi Wang and Hongxu Yin and Pavlo Molchanov and Yu-Chiang Frank Wang and Kwang-Ting Cheng and Min-Hung Chen},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2402.09353},
  archiveprefix = {arxiv},
}

@inproceedings{xu2024equivariant,
  title = {Equivariant Graph Neural Operator for Modeling {3D} Dynamics},
  author = {Xu, Minkai and Han, Jiaqi and Lou, Aaron and Kossaifi, Jean and Ramanathan, Arvind and Azizzadenesheli, Kamyar and Leskovec, Jure and Ermon, Stefano and Anandkumar, Anima},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2401.11037},
  archiveprefix = {arxiv},
}

@inproceedings{sun2024fedbpt,
  title = {{FedBPT}: {E}fficient Federated Black-box Prompt Tuning for Large Language Models},
  author = {Jingwei Sun and Ziyue Xu and Hongxu Yin and Dong Yang and Daguang Xu and Yudong Liu and Zhixu Du and Yiran Chen and Holger Roth},
  year = {2024},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2310.01467},
  archiveprefix = {arxiv},
}

@inproceedings{automaterss2024,
  title = {AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometries},
  author = {Bingjie Tang and Iretiayo Akinola and Jie Xu and Bowen Wen and Ankur Handa and Karl Van Wyk and Dieter Fox and Gaurav S. Sukhatme and Fabio Ramos and Yashraj Narang},
  year = {2024},
  month = {July},
  booktitle = {Robotics: Science and Systems (RSS)},
  eprint = {2407.08028},
  archiveprefix = {arxiv},
}

@inproceedings{goyal2024rvt2,
  title = {{RVT-2}: {L}earning Precise Manipulation from Few Demonstrations},
  author = {Ankit Goyal and Valts Blukis and Jie Xu and Yijie Guo and Yu-Wei Chao and Dieter Fox},
  year = {2024},
  month = {July},
  booktitle = {Robotics: Science and Systems (RSS)},
  eprint = {2406.08545},
  archiveprefix = {arxiv},
}

@article{azizzadeneshelisparse2024,
  title = {Sparse Contextual CDF Regression},
  author = {Kamyar Azizzadenesheli and William Lu and Anuran Makur and Qian Zhang},
  year = {2024},
  month = {July},
  journal = {Transactions on Machine Learning Research},
}

@inproceedings{tang2024nerftransformation,
  title = {{NeRFDeformer}: {NeRF} Transformation from a Single View via {3D} Scene Flows},
  author = {Zhenggang Tang and Zhongzheng Ren and Xiaoming Zhao and Bowen Wen and Jonathan Tremblay and Stan Birchfield and Alex Schwing},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2406.10543},
  archiveprefix = {arxiv},
}

@inproceedings{zhang2024sceneextra,
  title = {Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata},
  author = {Dongsu Zhang and Francis Williams and Zan Gojcic and Karsten Kreis and Sanja Fidler and Young Min Kim and Amlan Kar},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2406.08292},
  archiveprefix = {arxiv},
}

@inproceedings{wang2024pacerplus,
  title = {{PACER+}: {O}n-Demand Pedestrian Animation Controller in Driving Scenarios},
  author = {Jingbo Wang and Zhengyi Luo and Ye Yuan and Yixuan Li and Bo Dai},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2404.19722},
  archiveprefix = {arxiv},
}

@inproceedings{weng2024articulated,
  title = {Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects},
  author = {Yijia Weng and Bowen Wen and Jonathan Tremblay and Valts Blukis and Dieter Fox and Leonidas Guibas and Stan Birchfield},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2404.01440},
  archiveprefix = {arxiv},
}

@inproceedings{zhang2024hoidiffusion,
  title = {{HOIDiffusion}: {G}enerating Realistic {3D} Hand-Object Interaction Data},
  author = {Mengqi Zhang and Yang Fu and Zheng Ding and Sifei Liu and Zhuowen Tu and Xiaolong Wang},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2403.12011},
  archiveprefix = {arxiv},
}

@inproceedings{yang2024lr3d,
  title = {Improving Distant {3D} Object Detection Using {2D} Box Supervision},
  author = {Zetong Yang and Zhiding Yu and Chris Choy and Renhao Wang and Anima Anandkumar and Jose M. Alvarez},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2403.09230},
  archiveprefix = {arxiv},
}

@inproceedings{guo2024regiongpt,
  title = {{RegionGPT}: {T}owards Region Understanding Vision Language Model},
  author = {Qiushan Guo and Shalini De Mello and Hongxu Yin and Wonmin Byeon and Ka Chun Cheung and Yizhou Yu and Ping Luo and Sifei Liu},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2403.02330},
  archiveprefix = {arxiv},
}

@inproceedings{xia2024wildrgbd,
  title = {{RGBD} Objects in the Wild: {S}caling Real-World {3D} Object Learning from {RGB-D} Videos},
  author = {Hongchi Xia and Yang Fu and Sifei Liu and Xiaolong Wang},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2401.12592},
  archiveprefix = {arxiv},
}

@inproceedings{trevithick2024rendering,
  title = {What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs},
  author = {Alex Trevithick and Matthew Chan and Towaki Takikawa and Umar Iqbal and Shalini De Mello and Manmohan Chandraker and Ravi Ramamoorthi and Koki Nagano},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2401.02411},
  archiveprefix = {arxiv},
}

@inproceedings{ling2024aligngaussians,
  title = {Align Your {G}aussians: {T}ext-to-4{D} with Dynamic {3D} {G}aussians and Composed Diffusion Models},
  author = {Huan Ling and Seung Wook Kim and Antonio Torralba and Sanja Fidler and Karsten Kreis},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.13763},
  archiveprefix = {arxiv},
}

@inproceedings{yuan2024gavatar,
  title = {G{A}vatar: {A}nimatable 3{D} Gaussian Avatars with Implicit Mesh Learning},
  author = {Ye Yuan and Xueting Li and Yangyi Huang and Shalini De Mello and Koki Nagano and Jan Kautz and Umar Iqbal},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.11461},
  archiveprefix = {arxiv},
}

@inproceedings{wen2024fpose,
  title = {{FoundationPose}: {U}nified {6D} Pose Estimation and Tracking of Novel Objects},
  author = {Bowen Wen and Wei Yang and Jan Kautz and Stan Birchfield},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.08344},
  archiveprefix = {arxiv},
}

@inproceedings{lin2024vila,
  title = {VILA: On Pre-training for Visual Language Models},
  author = {Ji Lin and Hongxu Yin and Wei Ping and Yao Lu and Pavlo Molchanov and Andrew Tao and Huizi Mao and Jan Kautz and Mohammad Shoeybi and Song Han},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.07533},
  archiveprefix = {arxiv},
}

@inproceedings{yang2024nogs,
  title = {{COLMAP-Free} {3D} {G}aussian Splatting},
  author = {Yang Fu and Sifei Liu and Amey Kulkarni and Jan Kautz and Alexei A. Efros and Xiaolong Wang},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.07504},
  archiveprefix = {arxiv},
}

@inproceedings{ranzinger2024radio,
  title = {{AM-RADIO}: {A}gglomerative Vision Foundation Model Reduce All Domains Into One},
  author = {Mike Ranzinger and Greg Heinrich and Pavlo Molchanov and Jan Kautz},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.06709},
  archiveprefix = {arxiv},
}

@inproceedings{li2024ego,
  title = {Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?},
  author = {Zhiqi Li and Zhiding Yu and Shiyi Lan and Jiahan Li and Jan Kautz and Tong Lu and Jose M. Alvarez},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2312.03031},
  archiveprefix = {arxiv},
}

@inproceedings{zheng2024dream4d,
  title = {A Unified Approach for Text- and Image-guided 4D Scene Generation},
  author = {Yufeng Zheng and Xueting Li and Koki Nagano and Sifei Liu and Karsten Kreis and Otmar Hilliges and Shalini De Mello},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2311.16854},
  archiveprefix = {arxiv},
}

@inproceedings{xie2024perada,
  title = {{PerAda}: {P}arameter-Efficient Federated Learning Personalization with Generalization Guarantees},
  author = {Chulin Xie and De-An Huang and Wenda Chu and Daguang Xu and Chaowei Xiao and Bo Li and Anima Anandkumar},
  year = {2024},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2302.06637},
  archiveprefix = {arxiv},
}

@inproceedings{petrovich2024multi,
  title = {Multi-Track Timeline Control for Text-Driven 3{D} Human Motion Generation},
  author = {Mathis Petrovich and Or Litany and Umar Iqbal and Michael J. Black and G\"{u}l Varol and Xue Bin Peng and Davis Rempe},
  year = {2024},
  month = {June},
  booktitle = {CVPR Workshop on Human Motion Generation (HuMoGen)},
  eprint = {2401.08559},
  archiveprefix = {arxiv},
}

@inproceedings{waleffe2024Empiricalmamba,
  title = {An Empirical Study of Mamba-based Language Models},
  author = {Roger Waleffe and Wonmin Byeon and Duncan Riach and Brandon Norick and Vijay Korthikanti and Tri Dao and Albert Gu and Ali Hatamizadeh and Sudhakar Singh and Deepak Narayanan and Garvit Kulshreshtha and Vartika Singh and Jared Casper and Jan Kautz and Mohammad Shoeybi and Bryan Catanzaro},
  year = {2024},
  month = {June},
  booktitle = {ArXiv Preprint},
  eprint = {2406.07887},
  archiveprefix = {arxiv},
}

@inproceedings{li2024hydra,
  title = {Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation},
  author = {Li, Zhenxin and Li, Kailin and Wang, Shihao and Lan, Shiyi and Yu, Zhiding and Ji, Yishen and Li, Zhiqi and Zhu, Ziyue and Kautz, Jan and Wu, Zuxuan and Jiang, Yu-Gang and Alvarez, Jose M.},
  year = {2024},
  month = {June},
  booktitle = {ArXiv Preprint},
  eprint = {2406.06978},
  archiveprefix = {arxiv},
}

@inproceedings{bire2024,
  title = {{AI}-driven emulation of ocean dynamics on sub-seasonal scales},
  author = {Bire, Suyash and Kossaifi, Jean and Silvestri, Simone and Kovachki, Nikola and Azizzadenesheli, Kamyar and Hill, Chris N and Anandkumar, Anima},
  year = {2024},
  month = {May},
  booktitle = {ICLR Workshop on Climate Change AI},
}

@inproceedings{white2023speeding,
  title = {Guaranteed Approximation Bounds for Mixed-Precision Neural Operators},
  author = {White, Colin and Tu, Renbo and Kossaifi, Jean and Pekhimenko, Gennady and Azizzadenesheli, Kamyar and Anandkumar, Anima},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
}

@inproceedings{li2024tactile,
  title = {Learning to Jointly Understand Visual and Tactile Signals},
  author = {Yichen Li and Yilun Du and Chao Liu and Francis Williams and Michael Foshey and Benjamin Eckart and Jan Kautz and Joshua B. Tenenbaum and Antonio Torralba and Wojciech Matusik},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
}

@inproceedings{yu2024viddiff,
  title = {Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition},
  author = {Sihyun Yu and Weili Nie and De-An Huang and Boyi Li and Jinwoo Shin and Anima Anandkumar},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2403.14148},
  archiveprefix = {arxiv},
}

@inproceedings{schwarz2024wildfusion,
  title = {{WildFusion}: {L}earning 3D-Aware Latent Diffusion Models in View Space},
  author = {Katja Schwarz and Seung Wook Kim and Jun Gao and Sanja Fidler and Andreas Geiger and Karsten Kreis},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2311.13570},
  archiveprefix = {arxiv},
}

@inproceedings{fu2024genfields,
  title = {{3D} Reconstruction with Generalizable Neural Fields using Scene Priors},
  author = {Yang Fu and Shalini De Mello and Xueting Li and Amey Kulkarni and Jan Kautz and Xiaolong Wang and Sifei Liu},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2309.15164},
  archiveprefix = {arxiv},
}

@inproceedings{hatamizadeh2024fastervit,
  title = {{FasterViT}: {F}ast Vision Transformers with Hierarchical Attention},
  author = {Ali Hatamizadeh and Greg Heinrich and Hongxu Yin and Andrew Tao and Jose M. Alvarez and Jan Kautz and Pavlo Molchanov},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2306.06189},
  archiveprefix = {arxiv},
}

@inproceedings{ishfaq2023provable,
  title = {Provable and Practical: {E}fficient Exploration in Reinforcement Learning via Langevin Monte Carlo},
  author = {Ishfaq, Haque and Lan, Qingfeng and Xu, Pan and Mahmood, A Rupam and Precup, Doina and Anandkumar, Anima and Azizzadenesheli, Kamyar},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2305.18246},
  archiveprefix = {arxiv},
}

@inproceedings{mardani2024variational,
  title = {A Variational Perspective on Solving Inverse Problems with Diffusion Models},
  author = {Morteza Mardani and Jiaming Song and Jan Kautz and Arash Vahdat},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2305.04391},
  archiveprefix = {arxiv},
}

@inproceedings{zhou2024timing,
  title = {Timing as an Action: {L}earning When to Observe and Act},
  author = {Zhou, Helen and Huang, Audrey and Azizzadenesheli, Kamyar and Childers, David and Lipton, Zachary},
  year = {2024},
  month = {May},
  booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
}

@article{azizzadenesheli2024neural,
  title = {Neural operators for accelerating scientific simulations and design},
  author = {Azizzadenesheli, Kamyar and Kovachki, Nikola and Li, Zongyi and Liu-Schiaffini, Miguel and Kossaifi, Jean and Anandkumar, Anima},
  year = {2024},
  month = {April},
  journal = {Nature Reviews Physics},
  doi = {10.1038/s42254-024-00712-5},
  eprint = {2309.15325},
  archiveprefix = {arxiv},
}

@article{lee2023rsgim,
  title = {Robust Sound-Guided Image Manipulation},
  author = {Seung Hyun Lee and Hyung-gun Chi and Gyeongrok Oh and Wonmin Byeon and Sang Ho Yoon and Hyunje Park and Wonjun Cho and Jinkyu Kim and Sangpil Kim},
  year = {2024},
  month = {July},
  journal = {Neural Networks},
  volume = {175},
  eprint = {2208.14114},
  archiveprefix = {arxiv},
}

@inproceedings{lichy2024fovagnostic,
  title = {{FoVA-Depth}: {F}ield-of-View Agnostic Depth Estimation for Cross-Dataset Generalization},
  author = {Daniel Lichy and Hang Su and Abhishek Badki and Jan Kautz and Orazio Gallo},
  year = {2024},
  month = {March},
  booktitle = {International Conference on 3D Vision (3DV)},
  eprint = {2401.13786},
  archiveprefix = {arxiv},
}

@inproceedings{Kocabas2023pace,
  title = {{PACE}: {H}uman and Camera Motion Estimation from in-the-wild Videos},
  author = {Muhammed Kocabas and Ye Yuan and Pavlo Molchanov and Yunrong Guo and Michael Black and Otmar Hilliges and Jan Kautz and Umar Iqbal},
  year = {2024},
  month = {March},
  booktitle = {International Conference on 3D Vision (3DV)},
  eprint = {2310.13768},
  archiveprefix = {arxiv},
}

@inproceedings{sun2024partial,
  title = {Partial-View Object View Synthesis via Filtering Inversion},
  author = {Fan-Yun Sun and Jonathan Tremblay and Valts Blukis and Kevin Lin and Danfei Xu and Boris Ivanovic and Peter Karkus and Stan Birchfield and Dieter Fox and Ruohan Zhang and Yunzhu Li and Jiajun Wu and Marco Pavone and Nick Haber},
  year = {2024},
  month = {March},
  booktitle = {International Conference on 3D Vision (3DV)},
  eprint = {2304.00673},
  archiveprefix = {arxiv},
}

@article{shi2023broadband,
  title = {Broadband ground motion synthesis via generative adversarial neural operators: Development and validation},
  author = {Shi, Yaozhong and Lavrentiadis, Grigorios and Asimaki, Domniki and Ross, Zachary E and Azizzadenesheli, Kamyar},
  year = {2024},
  month = {March},
  journal = {Bulletin of the Seismological Society of America},
  doi = {10.1785/0120230207},
  eprint = {2309.03447},
  archiveprefix = {arxiv},
}

@article{zhengTMLR2024,
  title = {Fast Training of Diffusion Models with Masked Transformers},
  author = {Hongkai Zheng and Weili Nie and Arash Vahdat and Anima Anandkumar},
  year = {2024},
  month = {March},
  journal = {Transactions on Machine Learning Research},
  eprint = {2306.09305},
  archiveprefix = {arxiv},
}

@article{zhang2022functional,
  title = {Functional Linear Regression of Cumulative Distribution Functions},
  author = {Zhang, Qian and Makur, Anuran and Azizzadenesheli, Kamyar},
  year = {2024},
  month = {March},
  journal = {Transactions on Machine Learning Research},
}

@article{liu2023prismer,
  title = {Prismer: {A} Vision-Language Model with An Ensemble of Experts},
  author = {Liu, Shikun and Fan, Linxi and Johns, Edward and Yu, Zhiding and Xiao, Chaowei and Anandkumar, Anima},
  year = {2024},
  month = {March},
  journal = {Transactions on Machine Learning Research},
  eprint = {2303.02506},
  archiveprefix = {arxiv},
}

@inproceedings{ganj2024mobile,
  title = {Mobile {AR} Depth Estimation: Challenges \& Prospects},
  author = {Ashkan Ganj and Yiqin Zhao and Hang Su and Tian Guo},
  year = {2024},
  month = {February},
  booktitle = {International Workshop on Mobile Computing Systems and Applications},
  doi = {10.1145/3638550.3641122},
  eprint = {2310.14437},
  archiveprefix = {arxiv},
}

@article{kovachki2024operator,
  title = {Operator Learning: Algorithms and Analysis},
  author = {Kovachki, Nikola B and Lanthaler, Samuel and Stuart, Andrew M},
  year = {2024},
  month = {February},
  journal = {Handbook of Numerical Analysis},
  eprint = {2402.15715},
  archiveprefix = {arxiv},
}

@inproceedings{white2023physics,
  title = {Physics-informed neural operators with exact differentiation on arbitrary geometries},
  author = {White, Colin and Berner, Julius and Kossaifi, Jean and Elleithy, Mogab and Pitt, David and Leibovici, Daniel and Li, Zongyi and Azizzadenesheli, Kamyar and Anandkumar, Anima},
  year = {2023},
  month = {December},
  booktitle = {Symbiosis of Deep Learning and Differential Equations III, Neural Information Processing Systems (NeurIPS)},
}

@inproceedings{smith2023statespace,
  title = {Convolutional State Space Models for Long-Range Spatiotemporal Modeling},
  author = {Jimmy T.H. Smith and Shalini De Mello and Jan Kautz and Scott Linderman and Wonmin Byeon},
  year = {2023},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2310.19694},
  archiveprefix = {arxiv},
}

@inproceedings{li2024geometry,
  title = {Geometry-informed neural operator for large-scale {3D} {PDE}s},
  author = {Li, Zongyi and Kovachki, Nikola and Choy, Chris and Li, Boyi and Kossaifi, Jean and Otta, Shourya and Nabian, Mohammad Amin and Stadler, Maximilian and Hundt, Christian and Azizzadenesheli, Kamyar and Anandkumar, Anima},
  year = {2023},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2309.00583},
  archiveprefix = {arxiv},
}

@inproceedings{li2023generalizable,
  title = {Generalizable One-shot {3D} Neural Head Avatar},
  author = {Xueting Li and Shalini De Mello and Sifei Liu and Koki Nagano and Umar Iqbal and Jan Kautz},
  year = {2023},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2306.08768},
  archiveprefix = {arxiv},
}

@article{sun2023phase,
  title = {Phase Neural Operator for Multi-Station Picking of Seismic Arrivals},
  author = {Sun, Hongyu and Ross, Zachary E and Zhu, Weiqiang and Azizzadenesheli, Kamyar},
  year = {2023},
  month = {December},
  journal = {Geophysical Research Letters},
  doi = {10.1029/2023GL106434},
  eprint = {2305.03269},
  archiveprefix = {arxiv},
}

@inproceedings{mandlekar2023mimicgen,
  title = {{MimicGen}: {A} Data Generation System for Scalable Robot Learning using Human Demonstrations},
  author = {Ajay Mandlekar and Soroush Nasiriany and Bowen Wen and Iretiayo Akinola and Yashraj Narang and Linxi Fan and Yuke Zhu and Dieter Fox},
  year = {2023},
  month = {November},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2310.17596},
  archiveprefix = {arxiv},
}

@inproceedings{ozturkler2023smrd,
  title = {{SMRD}: SURE-based Robust {MRI} Reconstruction with Diffusion Models},
  author = {Batu Ozturkler and Chao Liu and Benjamin Eckart and Morteza Mardani and Jiaming Song and Jan Kautz},
  year = {2023},
  month = {October},
  booktitle = {International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)},
  eprint = {2310.01799},
  archiveprefix = {arxiv},
}

@inproceedings{zhao2023stl,
  title = {Fully Attentional Networks with Self-emerging Token Labeling},
  author = {Zhao, Bingyin and Yu, Zhiding and Lan, Shiyi and Cheng, Yutao and Anandkumar, Anima and Lao, Yingjie and Alvarez, Jose M.},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2401.03844},
  archiveprefix = {arxiv},
}

@inproceedings{cao2023texfusion,
  title = {{TexFusion}: {S}ynthesizing {3D} Textures with Text-Guided Image Diffusion Models},
  author = {Cao, Tianshi and Kreis, Karsten and Fidler, Sanja and Sharp, Nicholas and Yin, Kangxue},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2310.13772},
  archiveprefix = {arxiv},
}

@inproceedings{li2023dqtrack,
  title = {End-to-end 3{D} Tracking with Decoupled Queries},
  author = {Li, Yanwei and Yu, Zhiding and Philion, Jonah and Anandkumar, Anima and Fidler, Sanja and Jia, Jiaya and Alvarez, Jose M.},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  doi = {10.1109/ICCV51070.2023.01678},
}

@inproceedings{wang2023human,
  title = {Learning Human Dynamics in Autonomous Driving Scenarios},
  author = {Jingbo Wang and Ye Yuan and Zhengyi Luo and Kevin Xie and Dahua Lin and Umar Iqbal and Sanja Fidler and Sameh Khamis},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
}

@inproceedings{jeong2023tpos,
  title = {The Power of Sound ({TPoS}): {A}udio Reactive Video Generation with Stable Diffusion},
  author = {Yujin Jeong and Won Jeong Ryoo and Seung Hyun Lee and Da Bin Seo and Wonmin Byeon and Sangpil Kim and Jinkyu Kim},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2309.04509},
  archiveprefix = {arxiv},
}

@inproceedings{chen2023focalformer3d,
  title = {{FocalFormer3D}: {F}ocusing on Hard Instance for 3{D} Object Detection},
  author = {Chen, Yilun and Yu, Zhiding and Chen, Yukang and Lan, Shiyi and Anandkumar, Anima and Jia, Jiaya and Alvarez, Jose M.},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2308.04556},
  archiveprefix = {arxiv},
}

@inproceedings{li2023fbbev,
  title = {{FB-BEV}: {BEV} Representation from Forward-Backward View Transformations},
  author = {Zhiqi Li and Zhiding Yu and Wenhai Wang and Anima Anandkumar and Tong Lu and Jose M. Alvarez},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2308.02236},
  archiveprefix = {arxiv},
}

@inproceedings{li2023dreamteacher,
  title = {{DreamTeacher}: {P}retraining Image Backbones with Deep Generative Models},
  author = {Li, Daiqing and Ling, Huan and Kar, Amlan and Acuna, David and Kim, Seung Wook and Kreis, Karsten and Torralba, Antonio and Fidler, Sanja},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2307.07487},
  archiveprefix = {arxiv},
}

@inproceedings{chan2023genNVS,
  title = {Generative Novel View Synthesis with 3D-Aware Diffusion Models},
  author = {Eric Ryan Chan and Koki Nagano and Jeong Joon Park and Matthew Chan and Alexander William Bergman and Axel Levy and Miika Aittala and Shalini De Mello and Tero Karras and Gordon Wetzstein},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2304.02602},
  archiveprefix = {arxiv},
}

@inproceedings{iqbal2023rana,
  title = {RANA: Relightable Articulated Neural Avatars},
  author = {Umar Iqbal and Akin Caliskan and Koki Nagano and Sameh Khamis and Pavlo Molchanov and Jan Kautz},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2212.03237},
  archiveprefix = {arxiv},
}

@inproceedings{yuan2023physdiff,
  title = {{PhysDiff}: {P}hysics-Guided Human Motion Diffusion Model},
  author = {Ye Yuan and Jiaming Song and Umar Iqbal and Arash Vahdat and Jan Kautz},
  year = {2023},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2212.02500},
  archiveprefix = {arxiv},
}

@inproceedings{guo2023handal,
  title = {{HANDAL}: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions},
  author = {Andrew Guo and Bowen Wen and Jianhe Yuan and Jonathan Tremblay and Stephen Tyree and Jeffrey Smith and Stan Birchfield},
  year = {2023},
  month = {October},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  eprint = {2308.01477},
  archiveprefix = {arxiv},
}

@article{sun2023vvt,
  title = {Vicinity Vision Transformer},
  author = {Weixuan Sun and Zhen Qin and Hui Deng and Jianyuan Wang and Yi Zhang and Kaihao Zhang and Nick Barnes and Stan Birchfield and Lingpeng Kong and Yiran Zhong},
  year = {2023},
  month = {October},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  eprint = {2206.10552},
  archiveprefix = {arxiv},
}

@article{dockhorn2023private,
  title = {Differentially Private Diffusion Models},
  author = {Tim Dockhorn and Tianshi Cao and Arash Vahdat and Karsten Kreis},
  year = {2023},
  month = {October},
  journal = {Transactions on Machine Learning Research},
  eprint = {2210.09929},
  archiveprefix = {arxiv},
}

@article{zhang2023vid2player3d,
  title = {Learning Physically Simulated Tennis Skills from Broadcast Videos},
  author = {Zhang, Haotian and Yuan, Ye and Makoviychuk, Viktor and Guo, Yunrong and Fidler, Sanja and Peng, Xue Bin and Fatahalian, Kayvon},
  year = {2023},
  month = {Aug},
  journal = {ACM Transactions on Graphics (SIGGRAPH)},
  doi = {10.1145/3592408},
}

@article{lin2023texture,
  title = {Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization},
  author = {Connor Lin and Koki Nagano and Jan Kautz and Eric Chan and Umar Iqbal and Leonidas Guibas and Gordon Wetzstein and Sameh Khamis},
  year = {2023},
  month = {Aug},
  journal = {ACM Transactions on Graphics (SIGGRAPH)},
  eprint = {2305.03043},
  archiveprefix = {arxiv},
}

@article{trevithick2023portrait,
  title = {Real-Time Radiance Fields for Single-Image Portrait View Synthesis},
  author = {Alexander Trevithick and Matthew Chan and Michael Stengel and Eric Ryan Chan and Chao Liu and Zhiding Yu and Sameh Khamis and Manmohan Chandraker and Ravi Ramamoorthi and Koki Nagano},
  year = {2023},
  month = {Aug},
  journal = {ACM Transactions on Graphics (SIGGRAPH)},
  eprint = {2305.02310},
  archiveprefix = {arxiv},
}

@inproceedings{song2023lossguided,
  title = {Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation},
  author = {Jiaming Song and Qinsheng Zhang and Hongxu Yin and Morteza Mardani and Ming-Yu Liu and Jan Kautz and Yongxin Chen and Arash Vahdat},
  year = {2023},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
}

@inproceedings{liu2023schrodinger,
  title = {I^2SB: Image-to-Image Schr\"{o}dinger Bridge},
  author = {Guan-Horng Liu and Arash Vahdat and De-An Huang and Evangelos Theodorou and Weili Nie and Anima Anandkumar},
  year = {2023},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2302.05872},
  archiveprefix = {arxiv},
}

@inproceedings{zheng2023fastsampling,
  title = {Fast Sampling of Diffusion Models via Operator Learning},
  author = {Hongkai Zheng and Weili Nie and Arash Vahdat and Kamyar Azizzadenesheli and Anima Anandkumar},
  year = {2023},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2211.13449},
  archiveprefix = {arxiv},
}

@inproceedings{hatamizadeh2022global,
  title = {Global Context Vision Transformers},
  author = {Hatamizadeh, Ali and Yin, Hongxu and Heinrich, Greg and Kautz, Jan and Molchanov, Pavlo},
  year = {2023},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2206.09959},
  archiveprefix = {arxiv},
}

@inproceedings{madaan2023continual,
  title = {Heterogeneous Continual Learning},
  author = {Divyam Madaan and Hongxu Yin and Wonmin Byeon and Jan Kautz and Pavlo Molchanov},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2306.08593},
  archiveprefix = {arxiv},
}

@inproceedings{wang2023posetransfer,
  title = {Zero-shot Pose Transfer for Unrigged Stylized 3{D} Characters},
  author = {Jiashun Wang and Xueting Li and Sifei Liu and Shalini De Mello and Orazio Gallo and Xiaolong Wang and Jan Kautz},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2306.00200},
  archiveprefix = {arxiv},
}

@inproceedings{frosio2023a5,
  title = {{T}he {B}est {D}efense is a {Good} {O}ffense: {A}dversarial {A}ugmentation {A}gainst {A}dversarial {A}ttacks},
  author = {Iuri Frosio and Jan Kautz},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2305.14188},
  archiveprefix = {arxiv},
}

@inproceedings{dong2023grids,
  title = {Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids},
  author = {Wei Dong and Chris Choy and Charles Loop and Or Litany and Yuke Zhu and Anima Anandkumar},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2305.13220},
  archiveprefix = {arxiv},
}

@inproceedings{kim2023nfldm,
  title = {{NeuralField-LDM}: {S}cene Generation with Hierarchical Latent Diffusion Models},
  author = {Kim, Seung Wook and Brown, Bradley and Yin, Kangxue and Kreis, Karsten and Schwarz, Katja and Li, Daiqing and Rombach, Robin and Torralba, Antonio and Fidler, Sanja},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2304.09787},
  archiveprefix = {arxiv},
}

@inproceedings{blattmann2023videoldm,
  title = {Align your Latents: {H}igh-Resolution Video Synthesis with Latent Diffusion Models},
  author = {Blattmann, Andreas and Rombach, Robin and Ling, Huan and Dockhorn, Tim and Kim, Seung Wook and Fidler, Sanja and Kreis, Karsten},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2304.08818},
  archiveprefix = {arxiv},
}

@inproceedings{rempe2023trace,
  title = {Trace and Pace: {C}ontrollable Pedestrian Animation via Guided Trajectory Diffusion},
  author = {Rempe, Davis and Luo, Zhengyi and Peng, Xue Bin and Yuan, Ye and Kitani, Kris and Kreis, Karsten and Fidler, Sanja and Litany, Or},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2304.01893},
  archiveprefix = {arxiv},
}

@inproceedings{micaelli2023deepequilibrium,
  title = {Recurrence without Recurrence: {S}table Video Landmark Detection with Deep Equilibrium Models},
  author = {Paul Micaelli and Pavlo Molchanov and Arash Vahdat and Hongxu Yin and Jan Kautz},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2304.00600},
  archiveprefix = {arxiv},
}

@inproceedings{lee2023cope,
  title = {{TTA-COPE}: {T}est-Time Adaptation for Category-Level Object Pose Estimation},
  author = {Taeyeop Lee and Jonathan Tremblay and Valts Blukis and Bowen Wen and Byeong-Uk Lee and Inkyu Shin and Stan Birchfield and In So Kweon and Kuk-Jin Yoon},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2303.16730},
  archiveprefix = {arxiv},
}

@inproceedings{bundlesdfwen2023,
  title = {{BundleSDF}: {N}eural 6-{DoF} Tracking and {3D} Reconstruction of Unknown Objects},
  author = {Bowen Wen and Jonathan Tremblay and Valts Blukis and Stephen Tyree and Thomas M\"{u}ller and Alex Evans and Dieter Fox and Jan Kautz and Stan Birchfield},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2303.14158},
  archiveprefix = {arxiv},
}

@inproceedings{ye2023affordance,
  title = {Affordance Diffusion: {S}ynthesizing Hand-Object Interactions},
  author = {Yufei Ye and Xueting Li and Abhinav Gupta and Shalini De Mello and Stan Birchfield and Jiaming Song and Shubham Tulsiani and Sifei Liu},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2303.12538},
  archiveprefix = {arxiv},
}

@inproceedings{xu2023panoptic,
  title = {Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models},
  author = {Jiarui Xu and Sifei Liu and Arash Vahdat and Wonmin Byeon and Xiaolong Wang and Shalini De Mello},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2303.04803},
  archiveprefix = {arxiv},
}

@inproceedings{li2023voxformer,
  title = {{VoxFormer}: {S}parse voxel transformer for camera-based 3{D} semantic scene completion},
  author = {Li, Yiming and Yu, Zhiding and Choy, Christopher and Xiao, Chaowei and Alvarez, Jose M and Fidler, Sanja and Feng, Chen and Anandkumar, Anima},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2302.12251},
  archiveprefix = {arxiv},
}

@inproceedings{lan2023vision,
  title = {Vision Transformers Are Good Mask Auto-Labelers},
  author = {Lan, Shiyi and Yang, Xitong and Yu, Zhiding and Wu, Zuxuan and Alvarez, Jose M and Anandkumar, Anima},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2301.03992},
  archiveprefix = {arxiv},
}

@inproceedings{ruzzi2023gaze,
  title = {{GazeNeRF}: {3D}-{A}ware Gaze Redirection with Neural Radiance Fields},
  author = {Alessandro Ruzzi and Xiangwei Shi and Xi Wang and Gengyan Li and Shalini De Mello and Hyung Jin Chang and Xucong Zhang and Otmar Hilliges},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2212.04823},
  archiveprefix = {arxiv},
}

@inproceedings{lin2023magic3d,
  title = {{Magic3D}: {H}igh-Resolution Text-to-{3D} Content Creation},
  author = {Lin, Chen-Hsuan and Gao, Jun and Tang, Luming and Takikawa, Towaki and Zeng, Xiaohui and Huang, Xun and Kreis, Karsten and Fidler, Sanja and Liu, Ming-Yu and Lin, Tsung-Yi},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2211.10440},
  archiveprefix = {arxiv},
}

@inproceedings{yang2023hessian,
  title = {Global Vision Transformer Pruning with Hessian-Aware Saliency},
  author = {Huanrui Yang and Hongxu Yin and Maying Shen and Pavlo Molchanov and Hai Li and Jan Kautz},
  year = {2023},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2110.04869},
  archiveprefix = {arxiv},
}

@inproceedings{blukis2023oneshot,
  title = {One-Shot Neural Fields for {3D} Object Understanding},
  author = {Valts Blukis and Taeyeop Lee and Jonathan Tremblay and Bowen Wen and In So Kweon and Kuk-Jin Yoon and Dieter Fox and Stan Birchfield},
  year = {2023},
  month = {June},
  booktitle = {CVPR Workshop on Advances in NeRF for the Metaverse (XRNeRF)},
  eprint = {2210.12126},
  archiveprefix = {arxiv},
}

@inproceedings{li2023fbocc,
  title = {{FB-OCC}: 3{D} Occupancy Prediction based on Forward-Backward View Transformation},
  author = {Zhiqi Li and Zhiding Yu and David Austin and Mingsheng Fang and Shiyi Lan and Jan Kautz and Jose M. Alvarez},
  year = {2023},
  month = {June},
  booktitle = {CVPR Workshop on End-to-end Autonomous Driving},
  eprint = {2307.01492},
  archiveprefix = {arxiv},
}

@inproceedings{clemons2023leaf,
  title = {{A}ugmenting {L}egacy {N}etworks for {F}lexible {I}nference},
  author = {Jason Clemons and Iuri Frosio and Maying Shen and Jose M. Alvarez and Stephen W. Keckler},
  year = {2023},
  month = {June},
  booktitle = {IEEE Intelligent Vehicles Symposium},
}

@inproceedings{liu2023consisten,
  title = {Online Consistent Video Depth using Continuous Geometric Representations},
  author = {Chao Liu and Benjamin Eckart and Jan Kautz},
  year = {2023},
  month = {may},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
}

@inproceedings{tang2023tabletop,
  title = {{RGB}-{O}nly Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control},
  author = {Zhenggang Tang and Balakumar Sundaralingam and Jonathan Tremblay and Bowen Wen and Ye Yuan and Stephen Tyree and Charles Loop and Alexander Schwing and Stan Birchfield},
  year = {2023},
  month = {may},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2210.11668},
  archiveprefix = {arxiv},
}

@inproceedings{lin2023parallel,
  title = {Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation},
  author = {Yunzhi Lin and Thomas Muller and Jonathan Tremblay and Bowen Wen and Stephen Tyree and Alex Evans and Patricio A. Vela and Stan Birchfield},
  year = {2023},
  month = {may},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2210.10108},
  archiveprefix = {arxiv},
}

@inproceedings{singh2023progprompt,
  title = {{PROGPROMPT}: {G}enerating Situated Robot Task Plans using Large Language Models},
  author = {Ishika Singh and Valts Blukis and Arsalan Mousavian and Ankit Goyal and Danfei Xu and Jonathan Tremblay and Dieter Fox and Jesse Thomason and Animesh Garg},
  year = {2023},
  month = {may},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2209.11302},
  archiveprefix = {arxiv},
}

@inproceedings{song2023pseudoinverse,
  title = {Pseudoinverse-Guided Diffusion Models for Inverse Problems},
  author = {Song, Jiaming and Vahdat, Arash and Mardani, Morteza and Kautz, Jan},
  year = {2023},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
}

@inproceedings{yang2023gpvit,
  title = {{GPViT}: {A} High Resolution Non-Hierarchical Vision Transformer with Group Propagation},
  author = {Chenhongyi Yang and Jiarui Xu and Shalini De Mello and Elliot J. Crowley and Xiaolong Wang},
  year = {2023},
  month = {may},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2212.06795},
  archiveprefix = {arxiv},
}

@inproceedings{su2022dual,
  title = {Dual Diffusion Implicit Bridges for Image-to-Image Translation},
  author = {Su, Xuan and Song, Jiaming and Meng, Chenlin and Ermon, Stefano},
  year = {2023},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2203.08382},
  archiveprefix = {arxiv},
}

@inproceedings{yang2023re,
  title = {{Re-ViLM}: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning},
  author = {Zhuolin Yang and Wei Ping and Zihan Liu and Vijay Korthikanti and Weili Nie and De-An Huang and Linxi Fan and Zhiding Yu and Shiyi Lan and Bo Li and Ming-Yu Liu and Yuke Zhu and Mohammad Shoeybi and Bryan Catanzaro and Chaowei Xiao and Anima Anandkumar},
  year = {2023},
  month = {December},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP},
  eprint = {2302.04858},
  archiveprefix = {arxiv},
}

@article{hatamizadeh2022gradient,
  title = {Do Gradient Inversion Attacks Make Federated Learning Unsafe?},
  author = {Ali Hatamizadeh and Hongxu Yin and Pavlo Molchanov and Andriy Myronenko and Wenqi Li and Prerna Dogra and Andrew Feng and Mona G Flores and Jan Kautz and Daguang Xu and Holger R. Roth},
  year = {2023},
  month = {February},
  journal = {IEEE Transactions on Medical Imaging (TMI)},
  doi = {10.1109/TMI.2023.3239391},
  eprint = {2202.06924},
  archiveprefix = {arxiv},
}

@article{kovachki2023neural,
  title = {Neural Operator: Learning Maps Between Function Spaces With Applications to PDEs},
  author = {Nikola Kovachki and Zongyi Li and Burigede Liu and Kamyar Azizzadenesheli and Kaushik Bhattacharya and Andrew Stuart and Anima Anandkumar},
  year = {2023},
  journal = {Journal of Machine Learning Research},
  volume = {24},
  number = {89},
  pages = {1--97},
}

@inproceedings{labbe2022megapose,
  title = {{MegaPose}: {6D} Pose Estimation of Novel Objects via Render and Compare},
  author = {Yann Labb\`{e} and Lucas Manuelli and Arsalan Mousavian and Stephen Tyree and Stan Birchfield and Jonathan Tremblay and Justin Carpentier and Mathieu Aubry and Dieter Fox and Josef Sivic},
  year = {2022},
  month = {December},
  booktitle = {Conference on Robot Learning (CoRL)},
  eprint = {2212.06870},
  archiveprefix = {arxiv},
}

@inproceedings{meng2022concrete,
  title = {Concrete Score Matching: {G}eneralized Score Matching for Discrete Data},
  author = {Meng, Chenlin and Choi, Kristy and Song, Jiaming and Ermon, Stefano},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2211.00802},
  archiveprefix = {arxiv},
}

@inproceedings{shen2022structural,
  title = {Structural Pruning via Latency-Saliency Knapsack},
  author = {Shen, Maying and Yin, Hongxu and Molchanov, Pavlo and Mao, Lei and Liu, Jianna and Alvarez, Jose M},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2210.06659},
  archiveprefix = {arxiv},
}

@inproceedings{zeng2022lion,
  title = {{LION}: {L}atent Point Diffusion Models for {3D} Shape Generation},
  author = {Xiaohui Zeng and Arash Vahdat and Francis Williams and Zan Gojcic and Or Litany and Sanja Fidler and Karsten Kreis},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2210.06978},
  archiveprefix = {arxiv},
}

@inproceedings{dockhorn2022genie,
  title = {{GENIE}: {H}igher-Order Denoising Diffusion Solvers},
  author = {Tim Dockhorn and Arash Vahdat and Karsten Kreis},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2210.05475},
  archiveprefix = {arxiv},
}

@inproceedings{shu2022test,
  title = {Test-time prompt tuning for zero-shot generalization in vision-language models},
  author = {Shu, Manli and Nie, Weili and Huang, De-An and Yu, Zhiding and Goldstein, Tom and Anandkumar, Anima and Xiao, Chaowei},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2209.07511},
  archiveprefix = {arxiv},
}

@inproceedings{huang2022minvis,
  title = {{MinVIS}: A minimal video instance segmentation framework without video-based training},
  author = {Huang, De-An and Yu, Zhiding and Anandkumar, Anima},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2208.02245},
  archiveprefix = {arxiv},
}

@inproceedings{luo2022embodied,
  title = {Embodied Scene-aware Human Pose Estimation},
  author = {Luo, Zhengyi and Iwase, Shun and Yuan, Ye and Kitani, Kris},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2206.09106},
  archiveprefix = {arxiv},
}

@inproceedings{garg2022lisa,
  title = {{LISA}: {L}earning Interpretable Skill Abstractions from Language},
  author = {Garg, Divyansh and Vaidyanath, Skanda and Kim, Kuno and Song, Jiaming and Ermon, Stefano},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2203.00054},
  archiveprefix = {arxiv},
}

@inproceedings{kawar2022denoising,
  title = {Denoising Diffusion Restoration Models},
  author = {Kawar, Bahjat and Elad, Michael and Ermon, Stefano and Song, Jiaming},
  year = {2022},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2201.11793},
  archiveprefix = {arxiv},
}

@inproceedings{dong2021deep,
  title = {Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks},
  author = {Xin Dong and Hongxu Yin and Jose M Alvarez and Jan Kautz and Pavlo Molchanov and H. T. Kung},
  year = {2022},
  month = {November},
  booktitle = {British Machine Vision Conference (BMVC)},
  eprint = {2107.06304},
  archiveprefix = {arxiv},
}

@inproceedings{li2022scraping,
  title = {Scraping Textures from Natural Images for Synthesis and Editing},
  author = {Li, Xueting and Liu, Sifei and Wang, Xiaolong and Yang, Ming-Hsuan and Efros, Alyosha},
  year = {2022},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  doi = {10.1007/978-3-031-19784-0_23},
}

@inproceedings{NeuralObjectInsertion_ECCV22:2022,
  title = {Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion},
  author = {Zian Wang and Wenzheng Chen and David Acuna and Jan Kautz and Sanja Fidler},
  year = {2022},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2208.09480},
  archiveprefix = {arxiv},
}

@inproceedings{zhou2022avsbench,
  title = {Audio-Visual Segmentation},
  author = {Zhou, Jinxing and Wang, Jianyuan and Zhang, Jiayi and Sun, Weixuan and Zhang, Jing and Birchfield, Stan and Guo, Dan and Kong, Lingpeng and Wang, Meng and Zhong, Yiran},
  year = {2022},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2207.05042},
  archiveprefix = {arxiv},
}

@inproceedings{lee2022soundguided,
  title = {Sound-Guided Semantic Video Generation},
  author = {Seung Hyun Lee and Gyeongrok Oh and Wonmin Byeon and Chanyoung Kim and Won Jeong Ryoo and Sang Ho Yoon and Hyunjun Cho and Jihyun Bae and Jinkyu Kim and Sangpil Kim},
  year = {2022},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2204.09273},
  archiveprefix = {arxiv},
}

@inproceedings{cheng2022autoregressive,
  title = {Autoregressive {3D} shape generation via canonical mapping},
  author = {Cheng, An-Chieh and Li, Xueting and Liu, Sifei and Sun, Min and Yang, Ming-Hsuan},
  year = {2022},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2204.01955},
  archiveprefix = {arxiv},
}

@inproceedings{huang2022poegan,
  title = {Multimodal Conditional Image Synthesis with {Product-of-Experts GANs}},
  author = {Xun Huang and Arun Mallya and Ting-Chun Wang and Ming-Yu Liu},
  year = {2022},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2112.05130},
  archiveprefix = {arxiv},
}

@inproceedings{molchanov2022lana,
  title = {{LANA}: Latency Aware Network Acceleration},
  author = {Molchanov, Pavlo and Hall, Jimmy and Yin, Hongxu and Kautz, Jan and Fusi, Nicolo and Vahdat, Arash},
  year = {2022},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2107.10624},
  archiveprefix = {arxiv},
}

@inproceedings{tyree2022hope,
  title = {6-{DoF} Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark},
  author = {Tyree, Stephen and Tremblay, Jonathan and To, Thang and Cheng, Jia and Mosier, Terry and Smith, Jeffrey and Birchfield, Stan},
  year = {2022},
  month = {October},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  eprint = {2203.05701},
  archiveprefix = {arxiv},
}

@inproceedings{tremblay2022rtmv,
  title = {{RTMV}: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis},
  author = {Jonathan Tremblay and Moustafa Meshry and Alex Evans and Jan Kautz and Alexander Keller and Sameh Khamis and Thomas M{\"u}ller and Charles Loop and Nathan Morrical and Koki Nagano and Towaki Takikawa and Stan Birchfield},
  year = {2022},
  month = {Oct},
  booktitle = {ECCV Workshop on Learning to Generate 3D Shapes and Scenes},
  eprint = {2205.07058},
  archiveprefix = {arxiv},
}

@article{Vorontsov2022segim2im,
  title = {Towards Annotation-efficient Segmentation via Image-to-image Translation},
  author = {Eugene Vorontsov and Pavlo Molchanov and Matej Gazda and Christopher Beckham and Jan Kautz and Samuel Kadoury},
  year = {2022},
  month = {November},
  journal = {Medical Image Analysis},
  volume = {82},
  eprint = {1904.01636},
  archiveprefix = {arxiv},
}

@article{liu2022partial,
  title = {Partial Convolution for Padding, Inpainting, and Image Synthesis},
  author = {Liu, Guilin and Dundar, Aysegul and Shih, Kevin J and Wang, Ting-Chun and Reda, Fitsum A and Sapra, Karan and Yu, Zhiding and Yang, Xiaodong and Tao, Andrew and Catanzaro, Bryan},
  year = {2022},
  month = {September},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  doi = {10.1109/TPAMI.2022.3209702},
}

@inproceedings{nie2022diffpure,
  title = {Diffusion Models for Adversarial Purification},
  author = {Nie, Weili and Guo, Brandon and Huang, Yujia and Xiao, Chaowei and Vahdat, Arash and Anandkumar, Anima},
  year = {2022},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2205.07460},
  archiveprefix = {arxiv},
}

@inproceedings{zhou2022understanding,
  title = {Understanding The Robustness in Vision Transformers},
  author = {Zhou, Daquan and Yu, Zhiding and Xie, Enze and Xiao, Chaowei and Anandkumar, Animashree and Feng, Jiashi and Alvarez, Jose M},
  year = {2022},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2204.12451},
  archiveprefix = {arxiv},
}

@inproceedings{su2022scalingup,
  title = {Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework},
  author = {Jiahao Su and Wonmin Byeon and Furong Huang},
  year = {2022},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2106.09121},
  archiveprefix = {arxiv},
}

@inproceedings{mu2022coordgan,
  title = {{CoordGAN}: Self-Supervised Dense Correspondences Emerge from {GAN}s},
  author = {Mu, Jiteng and De Mello, Shalini and Yu, Zhiding and Vasconcelos, Nuno and Wang, Xiaolong and Kautz, Jan and Liu, Sifei},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2203.16521},
  archiveprefix = {arxiv},
}

@inproceedings{hatamizadeh2022gradvit,
  title = {{GradViT}: {G}radient Inversion of Vision Transformers},
  author = {Hatamizadeh, Ali and Yin, Hongxu and Roth, Holger R and Li, Wenqi and Kautz, Jan and Xu, Daguang and Molchanov, Pavlo},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2203.11894},
  archiveprefix = {arxiv},
}

@inproceedings{FreeSOLO_CVPR22:2022,
  title = {{FreeSOLO}: Learning to Segment Objects without Annotations},
  author = {Xinlong Wang and Zhiding Yu and Shalini De Mello and Jan Kautz and Animashree Anandkumar and Chunhua Shen and Jose M. Alvarez},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2202.12181},
  archiveprefix = {arxiv},
}

@inproceedings{Xu_2022_CVPR,
  title = {{GroupViT}: Semantic Segmentation Emerges From Text Supervision},
  author = {Xu, Jiarui and De Mello, Shalini and Liu, Sifei and Byeon, Wonmin and Breuel, Thomas and Kautz, Jan and Wang, Xiaolong},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2202.11094},
  archiveprefix = {arxiv},
}

@inproceedings{noguchi2022watch,
  title = {Watch It Move: {U}nsupervised Discovery of {3D} Joints for Re-Posing of Articulated Objects},
  author = {Noguchi, Atsuhiro and Iqbal, Umar and Tremblay, Jonathan and Harada, Tatsuya and Gallo, Orazio},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2112.11347},
  archiveprefix = {arxiv},
}

@inproceedings{Chan2021EG3D,
  title = {Efficient Geometry-aware {3D} Generative Adversarial Networks},
  author = {Eric Chan and Connor Z. Lin and Matthew A. Chan and Koki Nagano and Boxiao Pan and Shalini De Mello and Orazio Gallo and Leonidas J. Guibas and Jonathan Tremblay and Sameh Khamis and Tero Karras and Gordon Wetzstein},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2112.07945},
  archiveprefix = {arxiv},
}

@inproceedings{yin2022avit,
  title = {{A}-{V}i{T}: Adaptive Tokens for Efficient Vision Transformer},
  author = {Yin, Hongxu and Vahdat, Arash and Alvarez, Jose M. and Mallya, Arun and Kautz, Jan and Molchanov, Pavlo},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2112.07658},
  archiveprefix = {arxiv},
}

@inproceedings{yuan2022glamr,
  title = {{GLAMR}: {G}lobal Occlusion-Aware Human Mesh Recovery with Dynamic Cameras},
  author = {Yuan, Ye and Iqbal, Umar and Molchanov, Pavlo and Kitani, Kris and Kautz, Jan},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2112.01524},
  archiveprefix = {arxiv},
}

@inproceedings{Lee2022soundimage,
  title = {Sound-Guided Semantic Image Manipulation},
  author = {Seung Hyun Lee and Wonseok Roh and Wonmin Byeon and Sang Ho Yoon and Chan Young Kim and Jinkyu Kim and Sangpil Kim},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2112.00007},
  archiveprefix = {arxiv},
}

@inproceedings{shen2022prune,
  title = {When to Prune? {A} Policy towards Early Structural Pruning},
  author = {Shen, Maying and Molchanov, Pavlo and Yin, Hongxu and Alvarez, Jose M},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2110.12007},
  archiveprefix = {arxiv},
}

@inproceedings{li2022panoptic,
  title = {{Panoptic SegFormer}: Delving deeper into panoptic segmentation with transformers},
  author = {Li, Zhiqi and Wang, Wenhai and Xie, Enze and Yu, Zhiding and Anandkumar, Anima and Alvarez, Jose M and Luo, Ping and Lu, Tong},
  year = {2022},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2109.03814},
  archiveprefix = {arxiv},
}

@inproceedings{Wu2022rnndct,
  title = {Physics Informed {RNN-DCT} Networks for Time-Dependent Partial Differential Equations},
  author = {Benjamin Wu and Oliver Hennigh and Jan Kautz and Sanjay Choudhry and Wonmin Byeon},
  year = {2022},
  month = {June},
  booktitle = {International Conference on Computational Science (ICCS)},
  eprint = {2202.12358},
  archiveprefix = {arxiv},
}

@inproceedings{lin2022keypoint,
  title = {Keypoint-Based Category-Level Object Pose Tracking from an {RGB} Sequence with Uncertainty Estimation},
  author = {Lin, Yunzhi and Tremblay, Jonathan and Tyree, Stephen and Vela, Patricio A. and Birchfield, Stan},
  year = {2022},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2205.11047},
  archiveprefix = {arxiv},
}

@inproceedings{kamenev2022predictionnet,
  title = {{PredictionNet}: Real-Time Joint Probabilistic Traffic Prediction for Planning, Control, and Simulation},
  author = {Kamenev, Alexey and Wang, Lirui and Bohan, Ollin Boer and Kulkarni, Ishwar and Kartal, Bilal and Molchanov, Artem and Birchfield, Stan and Nist\'{e}r, David and Smolyanskiy, Nikolai},
  year = {2022},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2109.11094},
  archiveprefix = {arxiv},
}

@inproceedings{lin2022single,
  title = {Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an {RGB} Image},
  author = {Lin, Yunzhi and Tremblay, Jonathan and Tyree, Stephen and Vela, Patricio A. and Birchfield, Stan},
  year = {2022},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2109.06161},
  archiveprefix = {arxiv},
}

@article{xiao2022learning,
  title = {Learning contrastive representation for semantic correspondence},
  author = {Xiao, Taihong and Liu, Sifei and De Mello, Shalini and Yu, Zhiding and Kautz, Jan and Yang, Ming-Hsuan},
  year = {2022},
  month = {March},
  journal = {International Journal of Computer Vision (IJCV)},
  volume = {130},
  number = {5},
  pages = {1293--1309},
  eprint = {2109.10967},
  archiveprefix = {arxiv},
}

@article{Zhong2022displacement,
  title = {Displacement-Invariant Cost Computation for Efficient Stereo Matching},
  author = {Yiran Zhong and Charles Loop and Wonmin Byeon and Stan Birchfield and Yuchao Dai and Kaihao Zhang and Alexey Kamenev and Thomas Breuel and Hongdong Li and Jan Kautz},
  year = {2022},
  month = {May},
  journal = {International Journal of Computer Vision (IJCV)},
  volume = {130},
  number = {5},
  pages = {1196--1209},
  eprint = {2012.00899},
  archiveprefix = {arxiv},
}

@inproceedings{xiao2022ddgan,
  title = {Tackling the Generative Learning Trilemma with Denoising Diffusion {GAN}s},
  author = {Zhisheng Xiao and Karsten Kreis and Arash Vahdat},
  year = {2022},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2112.07804},
  archiveprefix = {arxiv},
}

@inproceedings{dockhorn2022cld,
  title = {Score-Based Generative Modeling with Critically-Damped Langevin Diffusion},
  author = {Tim Dockhorn and Arash Vahdat and Karsten Kreis},
  year = {2022},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2112.07068},
  archiveprefix = {arxiv},
}

@inproceedings{li2021learning,
  title = {Learning continuous environment fields via implicit functions},
  author = {Li, Xueting and De Mello, Shalini and Wang, Xiaolong and Yang, Ming-Hsuan and Kautz, Jan and Liu, Sifei},
  year = {2022},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2111.13997},
  archiveprefix = {arxiv},
}

@inproceedings{xie2022m,
  title = {{M$^2$BEV}: Multi-camera joint 3{D} detection and segmentation with unified birds-eye view representation},
  author = {Xie, Enze and Yu, Zhiding and Zhou, Daquan and Philion, Jonah and Anandkumar, Anima and Fidler, Sanja and Luo, Ping and Alvarez, Jose M},
  year = {2022},
  month = {April},
  booktitle = {ArXiv Preprint},
  eprint = {2204.05088},
  archiveprefix = {arxiv},
}

@inproceedings{raj2022dracon,
  title = {{DRaCoN}--Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars},
  author = {Raj, Amit and Iqbal, Umar and Nagano, Koki and Khamis, Sameh and Molchanov, Pavlo and Hays, James and Kautz, Jan},
  year = {2022},
  month = {March},
  booktitle = {ArXiv Preprint},
  eprint = {2203.15798},
  archiveprefix = {arxiv},
}

@inproceedings{wu2022interferometer,
  title = {Neural Interferometry: {I}mage Reconstruction from Astronomical Interferometers using Transformer-Conditioned Neural Fields},
  author = {Ben Wu and Chao Liu and Benjamin Eckart and Jan Kautz},
  year = {2022},
  month = {Feb},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  doi = {10.1609/aaai.v36i3.20171},
}

@inproceedings{yu2021coupled,
  title = {Coupled Segmentation and Edge Learning via Dynamic Graph Propagation},
  author = {Yu, Zhiding and Huang, Rui and Byeon, Wonmin and Liu, Sifei and Liu, Guilin and Breuel, Thomas and Anandkumar, Anima and Kautz, Jan},
  year = {2021},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
}

@inproceedings{cao2021dpsinkhorn,
  title = {Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence},
  author = {Cao, Tianshi and Bie, Alex and Vahdat, Arash and Fidler, Sanja and Kreis, Karsten},
  year = {2021},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2111.01177},
  archiveprefix = {arxiv},
}

@inproceedings{nie2021lace,
  title = {Controllable and Compositional Generation with Latent-Space Energy-Based Models},
  author = {Nie, Weili and Vahdat, Arash and Anandkumar, Anima},
  year = {2021},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2110.10873},
  archiveprefix = {arxiv},
}

@inproceedings{Dalal2021noretrain,
  title = {Improve Agents without Retraining: {P}arallel Tree Search with Off-Policy Correction},
  author = {Dalal, Gal and Hallak, Assaf and Dalton, Steven and Frosio, Iuri and Mannor, Shie and Chechik, Gal},
  year = {2021},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2107.01715},
  archiveprefix = {arxiv},
}

@inproceedings{vahdat2021score,
  title = {Score-based Generative Modeling in Latent Space},
  author = {Vahdat, Arash and Kreis, Karsten and Kautz, Jan},
  year = {2021},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2106.05931},
  archiveprefix = {arxiv},
}

@inproceedings{xie2021segformer,
  title = {{SegFormer}: Simple and efficient design for semantic segmentation with transformers},
  author = {Xie, Enze and Wang, Wenhai and Yu, Zhiding and Anandkumar, Anima and Alvarez, Jose M and Luo, Ping},
  year = {2021},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2105.15203},
  archiveprefix = {arxiv},
}

@inproceedings{aneja2021ncpvae,
  title = {A Contrastive Learning Approach for Training Variational Autoencoder Priors},
  author = {Aneja, Jyoti and Schwing, Alexander and Kautz, Jan and Vahdat, Arash},
  year = {2021},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2010.02917},
  archiveprefix = {arxiv},
}

@inproceedings{iqbal2021kama,
  title = {{KAMA}: 3{D} Keypoint Aware Body Mesh Articulation},
  author = {Iqbal, Umar and Xie, Kevin and Guo, Yunrong and Kautz, Jan and Molchanov, Pavlo},
  year = {2021},
  month = {December},
  booktitle = {International Conference on 3D Vision (3DV)},
  eprint = {2104.13502},
  archiveprefix = {arxiv},
}

@inproceedings{Prashnani2021NoiseAwareVS,
  title = {Noise-Aware Video Saliency Prediction},
  author = {Ekta Prashnani and Orazio Gallo and Joohwan Kim and Josef B. Spjut and Pradeep Sen and Iuri Frosio},
  year = {2021},
  month = {November},
  booktitle = {British Machine Vision Conference (BMVC)},
  eprint = {2104.08038},
  archiveprefix = {arxiv},
}

@inproceedings{HierCoMo_BMVC21:2021,
  title = {Hierarchical Contrastive Motion Learning for Video Action Recognition},
  author = {Xitong Yang and Xiaodong Yang and Sifei Liu and Deqing Sun and Larry Davis and Jan Kautz},
  year = {2021},
  month = {November},
  booktitle = {British Machine Vision Conference (BMVC)},
  eprint = {2007.10321},
  archiveprefix = {arxiv},
}

@inproceedings{mahmoud2021optimizing,
  title = {Optimizing Selective Protection for {CNN} Resilience},
  author = {Mahmoud, Abdulrahman and Hari, Siva Kumar Sastry and Fletcher, Christopher W and Adve, Sarita V and Sakr, Charbel and Shanbhag, Naresh and Molchanov, Pavlo and Sullivan, Michael B and Tsai, Timothy and Keckler, Stephen W},
  year = {2021},
  month = {October},
  booktitle = {International Symposium on Software Reliability Engineering (ISSRE)},
  doi = {10.1109/ISSRE52982.2021.00025},
}

@inproceedings{SSOD_ICCV21:2021,
  title = {Self-Supervised Object Detection via Generative Image Synthesis},
  author = {Siva Karthik Mustikovela and Shalini De Mello and Aayush Prakash and Umar Iqbal and Sifei Liu and Thu Nguyen-Phuoc and Carsten Rother and Jan Kautz},
  year = {2021},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2110.09848},
  archiveprefix = {arxiv},
}

@inproceedings{LearningIndoorLighting_ICCV21:2021,
  title = {Learning Indoor Inverse Rendering with {3D} Spatially-Varying Lighting},
  author = {Zian Wang and Jonah Philion and Sanja Fidler and Jan Kautz},
  year = {2021},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2109.06061},
  archiveprefix = {arxiv},
}

@inproceedings{hao2021GANcraft,
  title = {{GANcraft}: Unsupervised 3D Neural Rendering of Minecraft Worlds},
  author = {Zekun Hao and Arun Mallya and Serge Belongie and Ming-Yu Liu},
  year = {2021},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2104.07659},
  archiveprefix = {arxiv},
}

@inproceedings{prakash2021iccvrealtosim,
  title = {Self-Supervised Real-to-Sim Scene Generation},
  author = {Prakash, Aayush and Debnath, Shoubhik and Lafleche, Jean-Francois and Cameracci, Eric and State, Gavriel and Birchfield, Stan and Law, Marc T.},
  year = {2021},
  month = {October},
  booktitle = {IEEE International Conference on Computer Vision (ICCV)},
  eprint = {2011.14488},
  archiveprefix = {arxiv},
}

@inproceedings{lin2021mvml,
  title = {Multi-View Fusion for Multi-Level Robotic Scene Understanding},
  author = {Lin, Yunzhi and Tremblay, Jonathan and Tyree, Stephen and Vela, Patricio A. and Birchfield, Stan},
  year = {2021},
  month = {September},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  eprint = {2103.13539},
  archiveprefix = {arxiv},
}

@inproceedings{kumar2021jailer,
  title = {Joint Space Control via Deep Reinforcement Learning},
  author = {Kumar, Visak and Hoeller, David and Sundaralingam, Balakumar and Tremblay, Jonathan and Birchfield, Stan},
  year = {2021},
  month = {September},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  eprint = {2011.06332},
  archiveprefix = {arxiv},
}

@inproceedings{Ghodsi2021scenarios,
  title = {Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles},
  author = {Ghodsi, Zahra and Hari, Siva and Frosio, Iuri and Tsai, Timothy and Troccoli, Alejandro and Keckler, Stephen and Garg, Siddharth and Anandkumar, Anima},
  year = {2021},
  month = {March},
  booktitle = {IEEE Intelligent Vehicles Symposium},
  eprint = {2103.07403},
  archiveprefix = {arxiv},
}

@article{DomainStylization_TPAMI20:2021,
  title = {Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation},
  author = {Aysegul Dundar and Ming-Yu Liu and Zhiding Yu and Ting-Chun Wang and John Zedlewski and Jan Kautz},
  year = {2021},
  month = {July},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  volume = {43},
  number = {7},
}

@article{cheng2021rmpflow,
  title = {{RMPflow}: A Geometric Framework for Generation of Multi-Task Motion Policies},
  author = {Cheng, Ching-An and Mukadam, Mustafa and Issac, Jan and Birchfield, Stan and Fox, Dieter and Boots, Byron and Ratliff, Nathan},
  year = {2021},
  month = {jul},
  journal = {IEEE Transactions on Automation Science and Engineering (TASE)},
  volume = {18},
  number = {3},
  pages = {968--987},
  eprint = {2007.14256},
  archiveprefix = {arxiv},
}

@inproceedings{bhattad2021view,
  title = {View Generalization for Single Image Textured {3D} Models},
  author = {Bhattad, Anand and Dundar, Aysegul and Liu, Guilin and Tao, Andrew and Catanzaro, Bryan},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2106.06533},
  archiveprefix = {arxiv},
}

@inproceedings{idelbayev2021optimal,
  title = {Optimal Quantization Using Scaled Codebook},
  author = {Idelbayev, Yerlan and Molchanov, Pavlo and Shen, Maying and Yin, Hongxu and Carreira-Perpin{\'a}n, Miguel A and Alvarez, Jose M},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
}

@inproceedings{Ben2021SSLParAE,
  title = {Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models},
  author = {Benjamin Eckart and Wentao Yuan and Chao Liu and Jan Kautz},
  year = {2021},
  month = {june},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
}

@inproceedings{Kothari2021weaklysupervised,
  title = {Weakly-Supervised Physically Unconstrained Gaze Estimation},
  author = {Rakshit Kothari and Shalini De Mello and Umar Iqbal and Wonmin Byeon and Seonwook Park and Jan Kautz},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2105.09803},
  archiveprefix = {arxiv},
}

@inproceedings{lan2021discobox,
  title = {{DiscoBox}: {W}eakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision},
  author = {Lan, Shiyi and Yu, Zhiding and Choy, Christopher and Radhakrishnan, Subhashree and Liu, Guilin and Zhu, Yuke and Davis, Larry S and Anandkumar, Anima},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2105.06464},
  archiveprefix = {arxiv},
}

@inproceedings{yin2021gradinv,
  title = {See through Gradients: Image Batch Recovery via GradInversion},
  author = {Yin, Hongxu and Mallya, Arun and Vahdat, Arash and Alvarez, Jose M. and Kautz, Jan and Molchanov, Pavlo},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2104.07586},
  archiveprefix = {arxiv},
}

@inproceedings{chao2021dexycb,
  title = {{DexYCB}: A Benchmark for Capturing Hand Grasping of Objects},
  author = {Chao, Yu-Wei and Yang, Wei and Xiang, Yu and Molchanov, Pavlo and Handa, Ankur and Tremblay, Jonathan and Narang, Yashraj S. and Van Wyk, Karl and Iqbal, Umar and Birchfield, Stan and Kautz, Jan and Fox, Dieter},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2104.04631},
  archiveprefix = {arxiv},
}

@inproceedings{zhong2021sfm,
  title = {Deep Two-View Structure-from-Motion Revisited},
  author = {Wang, Jianyuan and Zhong, Yiran and Dai, Yuchao and Birchfield, Stan and Zhang, Kaihao and Smolyanskiy, Nikolai and Li, Hongdong},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2104.00556},
  archiveprefix = {arxiv},
}

@inproceedings{Fu_2021_CVPR,
  title = {Learning to Track Instances without Video Annotations},
  author = {Fu, Yang and Liu, Sifei and Iqbal, Umar and De Mello, Shalini and Shi, Humphrey and Kautz, Jan},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {8680-8689},
  eprint = {2104.00287},
  archiveprefix = {arxiv},
}

@inproceedings{yu2021dual,
  title = {Dual Contrastive Loss and Attention for {GAN}s},
  author = {Yu, Ning and Liu, Guilin and Dundar, Aysegul and Tao, Andrew and Catanzaro, Bryan and Davis, Larry S and Fritz, Mario},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2103.16748},
  archiveprefix = {arxiv},
}

@inproceedings{badki2021BiTTC,
  title = {{B}inary {TTC}: {A} Temporal Geofence for Autonomous Navigation},
  author = {Badki, Abhishek and Gallo, Orazio and Kautz, Jan and Sen, Pradeep},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2101.04777},
  archiveprefix = {arxiv},
}

@inproceedings{wang2021facevid2vid,
  title = {One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing},
  author = {Ting-Chun Wang and Arun Mallya and Ming-Yu Liu},
  year = {2021},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2011.15126},
  archiveprefix = {arxiv},
}

@inproceedings{Hennigh2021simnet,
  title = {{NVIDIA SimNet}: {A}n {AI}-accelerated multi-physics simulation framework},
  author = {Oliver Hennigh and Susheela Narasimhan and Mohammad Amin Nabian and Akshay Subramaniam and Kaustubh Tangsali and Max Rietmann and Jose del Aguila Ferrandis and Wonmin Byeon and Zhiwei Fang and Sanjay Choudhry},
  year = {2021},
  month = {June},
  booktitle = {International Conference on Computational Science (ICCS)},
  eprint = {2012.07938},
  archiveprefix = {arxiv},
}

@inproceedings{spurr2021adversarial,
  title = {Adversarial Motion Modelling Helps Semi-Supervised Hand Pose Estimation},
  author = {Spurr, Adrian and Molchanov, Pavlo and Iqbal, Umar and Kautz, Jan and Hilliges, Otmar},
  year = {2021},
  month = {June},
  booktitle = {ArXiv Preprint},
  eprint = {2106.05954},
  archiveprefix = {arxiv},
}

@inproceedings{zhu2021hier,
  title = {Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs},
  author = {Zhu, Yifeng and Tremblay, Jonathan and Birchfield, Stan and Zhu, Yuke},
  year = {2021},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2012.07277},
  archiveprefix = {arxiv},
}

@inproceedings{shi2021fastuq,
  title = {Fast Uncertainty Quantification for Deep Object Pose Estimation},
  author = {Shi, Guanya and Zhu, Yifeng and Tremblay, Jonathan and Birchfield, Stan and Ramos, Fabio and Anandkumar, Animashree and Zhu, Yuke},
  year = {2021},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {2011.07748},
  archiveprefix = {arxiv},
}

@inproceedings{Wang2021NeuralTF,
  title = {Neural Trajectory Fields for Dynamic Novel View Synthesis},
  author = {Chaoyang Wang and Ben Eckart and Simon Lucey and Orazio Gallo},
  year = {2021},
  month = {March},
  journal = {ArXiv Preprint},
  eprint = {2105.05994},
  archiveprefix = {arxiv},
}

@inproceedings{morrical2021nvisii,
  title = {{NViSII}: A Scriptable Tool for Photorealistic Image Generation},
  author = {Morrical, Nathan and Tremblay, Jonathan and Lin, Yunzhi and Tyree, Stephen and Birchfield, Stan and Pascucci, Valerio and Wald, Ingo},
  year = {2021},
  month = {May},
  booktitle = {ICLR Workshop on Synthetic Data Generation},
  eprint = {2105.13962},
  archiveprefix = {arxiv},
}

@inproceedings{MultiModalTransformer_ICLR21:2021,
  title = {Parameter Efficient Multimodal Transformers for Video Representation Learning},
  author = {Sangho Lee and Youngjae Yu and Gunhee Kim and Thomas Breuel and Jan Kautz and Yale Song},
  year = {2021},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2012.04124},
  archiveprefix = {arxiv},
}

@inproceedings{xiao2020vaebm,
  title = {{VAEBM}: A Symbiosis between Variational Autoencoders and Energy-based Models},
  author = {Xiao, Zhisheng and Kreis, Karsten and Kautz, Jan and Vahdat, Arash},
  year = {2021},
  month = {May},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2010.00654},
  archiveprefix = {arxiv},
}

@inproceedings{Jonnalagadda2021anticheat,
  title = {Robust Vision-Based Cheat Detection in Competitive Gaming},
  author = {Jonnalagadda, Aditya and Frosio, Iuri and Schneider, Seth and McGuire, Morgan and Kim, Joohwan},
  year = {2021},
  month = {March},
  booktitle = {ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games},
  eprint = {2103.10031},
  archiveprefix = {arxiv},
}

@inproceedings{li2020online,
  title = {Online adaptation for consistent mesh reconstruction in the wild},
  author = {Li, Xueting and Liu, Sifei and De Mello, Shalini and Kim, Kihwan and Wang, Xiaolong and Yang, Ming-Hsuan and Kautz, Jan},
  year = {2020},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  volume = {33},
  pages = {15009--15019},
  eprint = {2012.03196},
  archiveprefix = {arxiv},
}

@inproceedings{mardani2020neural,
  title = {Neural {FFT}s for Universal Texture Image Synthesis},
  author = {Mardani, Morteza and Liu, Guilin and Dundar, Aysegul and Liu, Shiqiu and Tao, Andrew and Catanzaro, Bryan},
  year = {2020},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
}

@inproceedings{Habtegebrial2020GenerativeVS,
  title = {Generative View Synthesis: {F}rom Single-view Semantics to Novel-view Images},
  author = {Tewodros Amberbir Habtegebrial and Varun Jampani and Orazio Gallo and Didier Stricker},
  year = {2020},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2008.09106},
  archiveprefix = {arxiv},
}

@inproceedings{vahdat2020NVAE,
  title = {{NVAE}: A Deep Hierarchical Variational Autoencoder},
  author = {Vahdat, Arash and Kautz, Jan},
  year = {2020},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2007.03898},
  archiveprefix = {arxiv},
}

@inproceedings{su2020convttlstm,
  title = {Convolutional Tensor-Train {LSTM} for Spatio-temporal Learning},
  author = {Jiahao Su and Wonmin Byeon and Jean Kossaifi and Furong Huang and Jan Kautz and Animashree Anandkumar},
  year = {2020},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2002.09131},
  archiveprefix = {arxiv},
}

@inproceedings{bernstein2020fromage,
  title = {On the Distance between Two Neural Networks and the Stability of Learning},
  author = {Bernstein, Jeremy and Vahdat, Arash and Yue, Yisong and Liu, Ming-Yu},
  year = {2020},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2002.03432},
  archiveprefix = {arxiv},
}

@inproceedings{Dalton2020cule,
  title = {Accelerating reinforcement learning through {GPU} atari emulation},
  author = {Steven Dalton and Iuri Frosio and Michael Garland},
  year = {2020},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {1907.08467},
  archiveprefix = {arxiv},
}

@inproceedings{tremblay2020indirect,
  title = {Indirect Object-to-Robot Pose Estimation from an External Monocular {RGB} Camera},
  author = {Tremblay, Jonathan and Tyree, Stephen and Mosier, Terry and Birchfield, Stan},
  year = {2020},
  month = {October},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  eprint = {2008.11822},
  archiveprefix = {arxiv},
}

@inproceedings{chen2020mvlidarnet,
  title = {{MVLidarNet}: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views},
  author = {Chen, Ke and Oldja, Ryan and Smolyanskiy, Nikolai and Birchfield, Stan and Popov, Alexander and Wehr, David and Eden, Ibrahim and Pehserl, Joachim},
  year = {2020},
  month = {October},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  eprint = {2006.05518},
  archiveprefix = {arxiv},
}

@inproceedings{UFO_ECCV20:2020,
  title = {{UFO2}: A Unified Framework towards Omni-supervised Object Detection},
  author = {Zhongzheng Ren and Zhiding Yu and Xiaodong Yang and Ming-Yu Liu and Alexander Schwing and Jan Kautz},
  year = {2020},
  month = {August},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2010.10804},
  archiveprefix = {arxiv},
}

@inproceedings{JointDisentanglingReID_ECCV20:2020,
  title = {Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification},
  author = {Yang Zou and Xiaodong Yang and Zhiding Yu and B. V. K. Vijaya Kumar and Jan Kautz},
  year = {2020},
  month = {August},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2007.10315},
  archiveprefix = {arxiv},
}

@inproceedings{mallya2020world,
  title = {World-Consistent Video-to-Video Synthesis},
  author = {Arun Mallya and Ting-Chun Wang and Karan Sapra and Ming-Yu Liu},
  year = {2020},
  month = {August},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2007.08509},
  archiveprefix = {arxiv},
}

@inproceedings{gupta2020infoground,
  title = {Contrastive Learning for Weakly Supervised Phrase Grounding},
  author = {Gupta, Tanmay and Vahdat, Arash and Chechik, Gal and Yang, Xiaodong and Kautz, Jan and Hoiem, Derek},
  year = {2020},
  month = {August},
  booktitle = {European Conference on Computer Vision (ECCV)},
  eprint = {2006.09920},
  archiveprefix = {arxiv},
}

@inproceedings{li2020self,
  title = {Self-supervised single-view {3D} reconstruction via semantic consistency},
  author = {Li, Xueting and Liu, Sifei and Kim, Kihwan and Mello, Shalini De and Jampani, Varun and Yang, Ming-Hsuan and Kautz, Jan},
  year = {2020},
  month = {October},
  booktitle = {European Conference on Computer Vision (ECCV)},
  pages = {677--693},
  eprint = {2003.06473},
  archiveprefix = {arxiv},
}

@inproceedings{AVH_ICML20:2020,
  title = {Angular Visual Hardness},
  author = {Beidi Chen and Weiyang Liu and Animesh Garg and Zhiding Yu and Anshumali Shrivastava and Jan Kautz and Anima Anandkumar},
  year = {2020},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {1912.02279},
  archiveprefix = {arxiv},
}

@inproceedings{vahdat2020undirectedpost,
  title = {Undirected Graphical Models as Approximate Posteriors},
  author = {Vahdat, Arash and Andriyash, Evgeny and Macready, William G},
  year = {2020},
  month = {july},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {1901.03440},
  archiveprefix = {arxiv},
}

@inproceedings{liu2020transposer,
  title = {Transposer: {U}niversal Texture Synthesis Using Feature Maps as Transposed Convolution Filter},
  author = {Liu, Guilin and Taori, Rohan and Wang, Ting-Chun and Yu, Zhiding and Liu, Shiqiu and Reda, Fitsum A and Sapra, Karan and Tao, Andrew and Catanzaro, Bryan},
  year = {2020},
  month = {July},
  booktitle = {ArXiv Preprint},
  eprint = {2007.07243},
  archiveprefix = {arxiv},
}

@inproceedings{Mahmoud2020pytorchfi,
  title = {{PyTorchFI}: {A} Runtime Perturbation Tool for {DNNs}},
  author = {Mahmoud, Abdulrahman and Aggarwal, Neeraj and Nobbe, Alex and Vicarte, Jose Rodrigo Sanchez and Adve, Sarita V. and Fletcher, Christopher W. and Frosio, Iuri and Hari, Siva Kumar Sastry},
  year = {2020},
  month = {June},
  booktitle = {IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)},
  doi = {10.1109/DSN-W50199.2020.00014},
}

@inproceedings{badki2020Bi3D,
  title = {{Bi3D}: {S}tereo Depth Estimation via Binary Classifications},
  author = {Badki, Abhishek and Troccoli, Alejandro and Kim, Kihwan and Kautz, Jan and Sen, Pradeep and Gallo, Orazio},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2005.07274},
  archiveprefix = {arxiv},
}

@inproceedings{InstanceAware_WSOD_CVPR20:2020,
  title = {Instance-aware, Context-focused, and Memory-efficient Weakly-Supervised Object Detection},
  author = {Zhongzheng Ren and Zhiding Yu and Xiaodong Yang and Ming-Yu Liu and Yong Jae Lee and Alexander Schwing and Jan Kautz},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2004.04725},
  archiveprefix = {arxiv},
}

@inproceedings{SSViewpointLearning_CVPR20:2020,
  title = {Self-Supervised Viewpoint Learning from Image Collections},
  author = {Siva Karthik Mustikovela and Varun Jampani and Shalini De Mello and Umar Iqbal and Sifei Liu and Carsten Rother and Jan Kautz},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2004.01793},
  archiveprefix = {arxiv},
}

@inproceedings{Yoon2020NovelVS,
  title = {Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular Camera},
  author = {Jae Shin Yoon and Kihwan Kim and Orazio Gallo and Hyun Soo Park and Jan Kautz},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2004.01294},
  archiveprefix = {arxiv},
}

@inproceedings{TwoShotBRDF_CVPR20:2020,
  title = {Two-shot Spatially-varying {BRDF} and Shape Estimation},
  author = {Mark Boss and Varun Jampani and Kihwan Kim and Hendrik Lensch and Jan Kautz},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2004.00403},
  archiveprefix = {arxiv},
}

@inproceedings{iqbal2020weakpose,
  title = {Weakly-Supervised 3{D} Human Pose Learning via Multi-view Images in the Wild},
  author = {Iqbal, Umar and Molchanov, Pavlo and Kautz, Jan},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2003.07581},
  archiveprefix = {arxiv},
}

@inproceedings{Badki2020Meshlets,
  title = {Meshlet Priors for {3D} Mesh Reconstruction},
  author = {Abhishek Badki and Orazio Gallo and Jan Kautz and Pradeep Sen},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {2001.01744},
  archiveprefix = {arxiv},
}

@inproceedings{vahdat2020unas,
  title = {{UNAS}: Differentiable Architecture Search Meets Reinforcement Learning},
  author = {Vahdat, Arash and Mallya, Arun and Liu, Ming-Yu and  Kautz, Jan},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {1912.07651},
  archiveprefix = {arxiv},
}

@inproceedings{ibrahim2020semi,
  title = {Semi-Supervised Semantic Image Segmentation with Self-correcting Networks},
  author = {Ibrahim, Mostafa S. and Vahdat, Arash and Ranjbar, Mani and Macready, William G.},
  year = {2020},
  month = {June},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  eprint = {1811.07073},
  archiveprefix = {arxiv},
}

@inproceedings{lee2020camerapose,
  title = {Camera-to-robot pose estimation from a single image},
  author = {Lee, Timothy E and Tremblay, Jonathan and To, Thang and Cheng, Jia and Mosier, Terry and Kroemer, Oliver and Fox, Dieter and Birchfield, Stan},
  year = {2020},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {1911.09231},
  archiveprefix = {arxiv},
}

@inproceedings{handa2019dexpilot,
  title = {{DexPilot}: {V}ision Based Teleoperation of Dexterous Robotic Hand-Arm System},
  author = {Handa, Ankur and Van Wyk, Karl and Yang, Wei and Liang, Jacky and Chao, Yu-Wei and Wan, Qian and Birchfield, Stan and Ratliff, Nathan and Fox, Dieter},
  year = {2020},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {1910.03135},
  archiveprefix = {arxiv},
}

@inproceedings{iqbal2020simtoreal,
  title = {Toward Sim-to-Real Directional Semantic Grasping},
  author = {Iqbal, Shariq and Tremblay, Jonathan and To, Thang and Cheng, Jia and Leitch, Erik and Campbell, Andy and Leung, Kirby and McKay, Duncan and Birchfield, Stan},
  year = {2020},
  month = {May},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  eprint = {1909.02075},
  archiveprefix = {arxiv},
}

@inproceedings{NRMVS_WACV20:2020,
  title = {{NRMVS}: Non-Rigid Multi-View Stereo},
  author = {Matthias Innmann and Kihwan Kim and Jinwei Gu and Matthias Niessner and Charles Loop and Marc Stamminger and Jan Kautz},
  year = {2020},
  month = {March},
  booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
  eprint = {1901.03910},
  archiveprefix = {arxiv},
}