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!

April 22, 2026

Honored to receive the NSF CAREER award! Huge thanks to my students, collaborators, and mentors who made this possible. Grateful to NSF for supporting our work.

March 19, 2026

A great article by UNC Research that discusses the background of our group's research on skill learning and video understanding. It also briefly describes my journey from being a basketball player to an AI researcher.

March 6, 2026

Gave a keynote talk "From Perception to Agency in Strategic Video Understanding" at the WACV 2026 Computer Vision for Winter Sports workshop held in Tucson, Arizona.

February 25, 2026

Gave a talk at Ai2 on our recently developed video benchmark for Strategic Video Intelligence. Stay tuned for more details and the public release!

February 9, 2026

Yulu showcasing his sports video understanding system to Chancellor Lee Roberts during the UNC Core AI event.

February 9, 2026

Gave a talk "From Pixels to Coaches: AI That Sees, Understands and Teaches" describing how our group's video understanding framework could give everyone access to world-class coaching by providing personalized feedback on skills from basketball to piano.

December 22, 2025

UNC published an article on our research to develop AI assistants that can understand human skills and help humans learn those skills more effectively.

December 4, 2025

Han presented his paper "ExAct: A Video-Language Benchmark for Expert Action Analysis" at NeurIPS'25 in San Diego.