Jim Rehg
Jim Rehg
Home
People
Join Us
News
Projects
Publications
Datasets
Teaching
Sponsors
Contact
STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
Junho Kim, Hosu Lee, James Matthew Rehg, Minsu Kim, Yong Man Ro
June 2026
PDF
Project
Type
Conference paper
Publications
Related
Exact Posterior Score Estimation for Solving Linear Inverse Problems
GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions
ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation
Toward Cognitive Supersensing in Multimodal Large Language Models
Cite
×
