Exact Posterior Score Estimation for Solving Linear Inverse Problems
NeurIPS 2026
Abbas Mammadov, Ozgur Kara, Kaan Oktay, Iskander Azangulov, Adil Kaan Akan, Hyungjin Chung, James Matthew Rehg, Yee Whye Teh
GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions
NeurIPS 2026
Junho Kim, Xu Cao, Houze Yang, Bikram Boote, Ana Jojic, Fiona Ryan, Bolin Lai, Sangmin Lee, James Matthew Rehg
ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
NeurIPS 2026
Brian Nlong Zhao, Ozgur Kara, Junho Kim, James Matthew Rehg
Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation
NeurIPS 2026, E&D Track
Yutong Liu, Nan Huang, Xu Cao, James Matthew Rehg
Toward Cognitive Supersensing in Multimodal Large Language Models
NeurIPS 2026
Boyi Li, Yifan Shen, Yuanzhe Liu, Yifan Xu, Jiateng Liu, Xinzhuo Li, Zhengyuan Li, Jingyuan Zhu, Yunhan Zhong, Lan Fangzhou, Jianguo Cao, James Matthew Rehg, Heng Ji, Ismini Lourentzou, Xu Cao
ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback
EMNLP 2026, Findings
Tarik Can Ozden, Sachidanand VS, Furkan Horoz, Ozgur Kara, Dilek Hakkani-Tur, Junho Kim, James Matthew Rehg
Decoding Children's Gait Behavior
ECCV 2026
Yifan Shen, Boyi Li, Meihuan Huang, Yuanzhe Liu, Xu Cao, Jinyang Jin, Zhengyuan Li, Anglin Liu, Junho Kim, Jingyuan Zhu, Lan Fangzhou, Jianguo Cao, Jintai Chen, Ismini Lourentzou, James Matthew Rehg
Kirin: Animal Motion Generation from In-the-Wild Video
ECCV 2026
Brian Nlong Zhao, Zhuoyang Pan, James Matthew Rehg, Jiajun Wu, Shangzhe Wu
Layer-Aware Video Composition via Split-then-Merge
ECCV 2026
Ozgur Kara, Yujia Chen, Ming-Hsuan Yang, James Matthew Rehg, Wen-Sheng Chu, Du Tran
Narrative-Driven Paper-to-Slide Generation via ArcDeck
ECCV 2026
Tarik Can Ozden, Sachidanand VS, Furkan Horoz, Ozgur Kara, Junho Kim, James Matthew Rehg
STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
ECCV 2026
Junho Kim, Hosu Lee, James Matthew Rehg, Minsu Kim, Yong Man Ro
CoherentHand: Temporally Consistent 3D Hand Trajectory Synthesis with Semantic Motion Priors
CVPR 2026, Findings
Bikram Boote, Junho Kim, Ozgur Kara, Sangmin Lee, James Matthew Rehg
Forecasting 3D Scanpaths in Egocentric Video
CVPR 2026
Fiona Ryan, Ishwarya Ananthabhotla, Yijun Qian, Judy Hoffman, James Matthew Rehg, Vamsi Krishna Ithapu, Calvin Murdock
Gaze Target Estimation Anywhere with Concepts
CVPR 2026
Xu Cao, Houze Yang, Vipin Gunda, Zhongyi Zhou, Tianyu Xu, Adarsh Kowdle, Inki Kim, James Matthew Rehg
How Much 3D Do Video Foundation Models Encode?
CVPR 2026
Zixuan Huang, Xiang Li, Zhaoyang Lv, James Matthew Rehg
Learning Predictive Visuomotor Coordination
CVPR 2026, Findings
Wenqi Jia, Bolin Lai, Miao Liu, Danfei Xu, James Matthew Rehg
Omni-MMSI: Toward Identity-attributed Social Interaction Understanding
CVPR 2026
Xinpeng Li, Bolin Lai, Hardy Chen, Shijian Deng, Cihang Xie, Yuyin Zhou, James Matthew Rehg, Yapeng Tian
Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective
CVPR 2026
Bolin Lai, Xudong Wang, Saketh Rambhatla, James Matthew Rehg, Zsolt Kira, Rohit Girdhar, Ishan Misra
Vinedresser3D: Agentic Text-guided 3D Editing
CVPR 2026
Yankuan Chi, Xiang Li, Zixuan Huang, James Matthew Rehg
DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing
ICLR 2026
Tarik Can Ozden, Ozgur Kara, Oguzhan Akcin, Kerem Zaman, Shashank Srivastava, Sandeep P. Chinchali, James Matthew Rehg