Gedas Bertasius

Assistant Professor

I am an Assistant Professor in the Computer Science department at the University of North Carolina, Chapel Hill. Before joining UNC, I was a postdoctoral researcher at Facebook AI Research (FAIR) working with Lorenzo Torresani. I finished my Ph.D. at the University of Pennsylvania, advised by Jianbo Shi, and my undergraduate degree at Dartmouth College.

About Me

Research

I lead the Multimodal Video Perception (MVP) group at UNC. We develop foundational models for multimodal video understanding, enabling machines to comprehend, reason about, and interact with complex video, audio, and language data. Moving beyond perception, we ask: what spatiotemporal abstractions are needed for AI to truly grasp complex human behaviors over long horizons? Representative projects include TimeSformer, Video ReCap, LLoVi, BIMBA, VideoTree.

Video Recognition

Developing spatiotemporal models for automatic video analysis (e.g., TimeSformer, ViS4mer).

Multimodal AI

Building models that can learn from video, audio, and text (e.g., Video ReCap, LLoVi, BIMBA).

Perceptual AI Coaches

Sports & AI

Developing AI models that can assist people with daily tasks and skill learning (e.g., VidAssist, Ego-Exo4D, and ExAct).

Video for Robotics

Elevating strategic insights using state-of-the-art multimodal video models (e.g., SVI-Bench, BASKET).

Generative Video Modeling

Translating visual inputs into effective real-world actions (e.g., WatchAct, BOSS, ReBot, and ARCADE)

Enabling applications such as multimodal video generation and editing (e.g., VMAs, AvED, V2M-Zero, and TeDiO)

Learn More

Recent News

June 1, 2026

We just released SVI-Bench, a large-scale benchmark for strategic reasoning over real-world, multi-agent video, built on team sports. Our main finding is that best video models do reasonably well on perception (74% on fine-grained video QA) but struggle significantly with higher-level reasoning (only 5% on the hardest agentic tasks). Shout out to my students Yulu, Han, Seongsu, Emon and Ben for worked tirelessly to make this happen!