Publications

Our publications provide insight into some of our leading-edge research.

Filters

Filters

Publication Year

Research Areas

Events

2026

Imitation Learning of Avoidance Modes for Efficient Multimodal Model Predictive Control
Changyu Lee, Byung-Kwan Lee, Kanghoon Yoon
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Minki Kang, Ryo Hachiuma, Shaokun Zhang, Subhashree Radhakrishnan, Yonggan Fu, Jindong Jiang, Mingjie Liu, Ehsan Hosseini-Asl, Yi Dong, Yu-Chiang Frank Wang, Byung-Kwan Lee
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Ali Hatamizadeh, Yejin Choi, Jan Kautz
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Byung-Kwan Lee, Ximing Lu, Shizhe Diao, Minki Kang, Saurav Muralidharan, Karan Sapra, Andrew Tao, Frank Wang, Ryo Hachiuma
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
Siyan Zhao, Yonggan Fu, Jindong Jiang, Shih-Yang Liu, Song Bian, Byung-Kwan Lee, Sharath Turuvekere Sreenivas, Wenliang Dai, Hanrong Ye, Aditya Grover, Pavlo Molchanov
EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation
Zeru Shi, Jindong Jiang, Ryo Hachiuma, Yonggan Fu, Byung-Kwan Lee, Peter Belcak, Saurav Muralidharan, Ayush Agarwal, Ruixiang Tang, Ambrish Dantrey, Pavlo Molchanov, Anjul Patney, Subhashree Radhakrishnan
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Minki Kang, Shizhe Diao, Ryo Hachiuma, Sung Ju Hwang, Pavlo Molchanov, Yu-Chiang Frank Wang, Byung-Kwan Lee
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su, Byung-Kwan Lee, Chan Hee Song, Sifei Liu, Subhashree Radhakrishnan, Seungryong Kim, Yu-Chiang Frank Wang, Min-Hung Chen
Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee, Jeany Son
cuArms: GPU-Accelerated Conflict-Based Planning for Multi-Arm Manipulation
Philip Huang, Fabio Ramos, Jiaoyang Li, Caelan Garrett, Lars Johannsmeier
DemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from Demonstration
Caelan Garrett, Neel Jawale, Fabio Ramos
TAMPAgent: Agentic Belief-Space Planning for Mobile Manipulation
Utkarsh Aashu Mishra, Alperen Degirmenci, Yongxin Chen, Danfei Xu, Tucker Hermans, Caelan Garrett
Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning
Shuo Cheng, Chuye Zhang, Alfred Cueva, Caelan Garrett, Ajay Mandlekar, Danfei Xu
Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data
Rafał Karp, Gene Liu, Shih-Hsin Li, Eric Courtemanche, Shengze Wang, Josef Spjut, David Pankratz, Mischa Kolbe, Michael Stengel, Sven Elflein, Adam Grygielski, Liwen Wu, Anjul Patney
Relight: Simple, User-Level Checkpointing and Fast Forward Replay for Distributed Task-Based Systems
Elliott Slaughter, Rupanshu Soi, Michael Bauer, Alex Aiken
ShareMMU: Supporting Secure Address Translation Sharing among Untrusted Accelerators
Faiz Alam , Mohamed Tarek Ibn Ziad, Yuanchao Xu, Abdulrahman Mahmoud, Greg Byrd, Aamer Jaleel
CUDA-Q Logical: Retargetable Compilation for Fault Tolerant Quantum Computing
Alexander McCaskey, Justin Lietz, Adam Holmes, Kohei Nakaji, Vadym Kliuchnikov, Yifan Hong, Amalee WIlson, Andres Paz, Bettina Heim, Bruno Schmitt, Krysta M. Svore
Composing Detector Error Models
Vadym Kliuchnikov, Justin Lietz, Fernando Pastawski
GenRecal: Generation after Recalibration from Large to Small Vision-Language Models
Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro, Yu-Chiang Frank Wang, Yueh-Hua Wu
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
Jiwan Kim, Kibum Kim, Wonjoong Kim, Byung-Kwan Lee, Chanyoung Park
Trusted Hardware Acceleration for Function Secret Sharing
Pengzhi Huang, Kiwan Maeng, G. Edward Suh
HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers
Jing Yang, Mayoore Jaiswal, Zian Wang, Xiao Steven Zeng, Yajie Zhao, Rochelle Pereira, Jianyuan Min
FusionRelight: Relighting Portraits in Real Time via Hybrid Domain Knowledge Fusion
Qian Huang, Mayoore Selvarasa Jaiswal, Zhen Zhong, Rochelle Pereira, Jianyuan Min
PIPES: Securing Agent Perception with Provenance and Priors
Sanjay Kariyappa, Severin Klingler, Edward Suh
Adaptive Time Delay for Improving Player Experience and Fairness in First-Person Shooter Games with Network Latency
Samin Shahriar Tokey, Ben Boudaoud, Josef Spjut, Mark Claypool
Impact of Frametime Spikes on Performance and Quality of Experience in Platformer Games
Samin Shahriar Tokey, Ben Boudaoud, Josef Spjut, Mark Claypool
Addressable Memory for Video World Models
Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Jonathan Lorraine, Aljoša Ošep
Best Paper, Oral F2S Workshop
Effects of Frame Rates up to 500 Hz on First Person Shooter Game Players
Samin Shahriar Tokey, Ben Boudaoud, Joohwan Kim, Josef Spjut, Mark Claypool
FastGen-PDD: Parallel Decoding Distillation for Image and Video Generation
Neta Shaul, Chao Liu, Arash Vahdat, Julius Berner
Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
Patrick Rim, Tom Long, Ekta Prashnani, Ruth Rosenholtz, Ben Boudaoud, Peter Xenopoulos, Alex Wong, Joohwan Kim, Jae-Hyun Jung
GalaxyDiT: Efficient Video Generation with Guidance Alignment and Adaptive Proxy in Diffusion Transformers
Zoey Song, Steve Dai, Ben Keller, Brucek Khailany
Performance, Rendering, and Interaction in Competitive Esports (PRICE)
Josef Spjut, Benjamin Watson, Madison Klarkowski, Rulon Raymond, Mark Claypool, Paul Ritaldato