Publications | Research

2022

A bidirectional formulation for Walk on Spheres

Yang Qi, Dario Seyb, Benedikt Bitterli, Wojciech Jarosz

Spatiotemporal Blue Noise Masks

Alan Wolfe, Nathan Morrical, Tomas Akenine-Möller, Ravi Ramamoorthi

Adaptive Neural Network-based OFDM Receivers

Moritz Benedikt Fischer, Sebastian Dörner, Sebastian Cammerer, Takayuki Shimizu, Hongsheng Lu, Stephan ten Brink

Diffusion Models for Adversarial Purification

Weili Nie, Brandon Guo, Yujia Huang, Chaowei Xiao, Arash Vahdat, Anima Anandkumar

ICML

CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs

Jiteng Mu, Shalini De Mello, Zhiding Yu, Nuno Vasconcelos, Xiaolong Wang, Sifei Liu

CVPR

GPU-Accelerated Partially Linear Multiuser Detection for 5G and Beyond URLLC Systems

Matthias Mehlhose, Guillermo Marcus, Daniel Schäufele, Daniyal Amir Awan, Nikolaus Binder, Martin Kasparick, Renato L. G. Cavalcante, Sławomir Stanćzak , Alex Keller

Exploiting Temporal Data Diversity for Detecting Safety-critical Faults in AV Compute Systems

Saurabh Jha, Shengkun Cui, Timothy Tsai, Siva Hari, Michael B. Sullivan, Zbigniew T. Kalbarczyk, Steve Keckler, Ravishankar K. Iyer

Correcting Robot Plans with Natural Language Feedback

Pratyusha Sharma, Balakumar Sundaralingam, Valts Blukis, Chris Paxton, Tucker Hermans, Antonio Torralba, Jacob Andreas, Dieter Fox

Ruby: Improving Hardware Efficiency for Tensor Algebra Accelerators Through Imperfect Factorization

Mark Horeni, Pooria Taheri, Po-An Tsai, Angshuman Parashar, Joel Emer, Siddharth Joshi

Whose Track Is It Anyway? Improving Robustness to Tracking Errors with Affinity-Based Prediction

Xinshuo Weng, Boris Ivanovic, Kris Kitani, Marco Pavone

CVPR

ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planning

Yuxiao Chen, Boris Ivanovic, Marco Pavone

Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps

Seung Wook Kim, Karsten Kreis, Daiqing Li, Antonio Torralba, Sanja Fidler

CVPR

GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras

Ye Yuan, Umar Iqbal, Pavlo Molchanov, Kris Kitani, Jan Kautz

CVPR

Ifor: Iterative flow minimization for robotic object rearrangement

Ankit Goyal, Arsalan Mousavian, Chris Paxton, Yu-Wei Chao, Brian Okorn, Jia Deng, Dieter Fox

GroupViT: Semantic Segmentation Emerges from Text Supervision

Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang

CVPR

FreeSOLO: Learning to Segment Objects without Annotations

Xinlong Wang, Zhiding Yu, Shalini De Mello, Jan Kautz, Anima Anandkumar, Chunhua Shen, Jose M. Alvarez

Efficient Geometry-aware 3D Generative Adversarial Networks

Eric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, Gordon Wetzstein

Oral

BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations

Daiqing Li, Huan Ling, Seung Wook Kim, Karsten Kreis, Adela Barriuso, Sanja Fidler, Antonio Torralba

CVPR

Mixed-Proxy Extensions for the NVIDIA PTX Memory Consistency Model

Daniel Lustig, Simon Cooksey, Olivier Giroux

IEEE Micro Top Picks in Computer Architecture (Honorable Mention)

A 0.297-pJ/bit 50.4-Gb/s/wire Inverter-Based Short-Reach Simultaneous Bidirectional Transceiver for Die-to-Die Interface in 5nm CMOS

Yoshinori Nishi, John W. Poulton, Xi Chen, Sanquan Song, Brian Zimmer, Walker Turner, Stephen Tell, Nikola Nedovic, John Wilson, William Dally, Tom Gray

A 17–95.6 TOPS/W Deep Learning Inference Accelerator with Per-Vector Scaled 4-bit Quantization for Transformers in 5nm

Ben Keller, Rangharajan Venkatesan, Steve Dai, Stephen Tell, Brian Zimmer, William Dally, Tom Gray, Brucek Khailany

Optimizing tensor network contraction using reinforcement learning

Eli Meirom, Haggai Maron, Shie Mannor, Gal Chechik

ICML

SIMD^2: A Generalized Matrix Instruction Set for Accelerating Tensor Computation beyond GEMM

Yunan Zhang, Po-An Tsai, Hung-Wei Tseng

A Formalism of DNN Accelerator Flexibility

Sheng-Chun Kao, Hyoukjun Kwon, Michael Pellauer, Angshuman Parashar, Tushar Krishna

Injecting Planning-Awareness into Prediction and Detection Evaluation

Boris Ivanovic, Marco Pavone

MTP: Multi-Hypothesis Tracking and Prediction for Reduced Error Propagation

Xinshuo Weng, Boris Ivanovic, Marco Pavone

Interaction-Dynamics-Aware Perception Zones for Obstacle Detection Safety Evaluation

Sever Topan, Karen Leung, Yuxiao Chen, Pritish Tupekar, Edward Schmerling, Jonas Nilsson, Michael Cox, Marco Pavone

Onesweep: A Faster Least Significant Digit Radix Sort for GPUs

Andrey Adinets, Duane Merrill

Finding the Right Recipe for Low Resource Domain Adaptation in Neural Machine Translation

Virginia Adams, Sandeep Subramanian, Mike Chrzanowski, Oleksii Hrinchuk, Oleksii Kuchaiev

A-ViT: Adaptive Tokens for Efficient Vision Transformer

Hongxu Danny Yin, Arash Vahdat, Jose M. Alvarez, Arun Mallya, Jan Kautz, Pavlo Molchanov

CVPR

When to Prune? A Policy towards Early Structural Pruning

Maying Shen, Pavlo Molchanov, Hongxu Danny Yin, Jose M. Alvarez

CVPR

GradViT: Gradient Inversion of Vision Transformers

Ali Hatamizadeh, Hongxu Danny Yin, Holger Roth, Wenqi Li, Jan Kautz, Daguang Xu, Pavlo Molchanov

CVPR