← Search

Lin Fu

1 accepted papers

2026

VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding

ICML 2026spotlight

We introduce VideoKR, the first large-scale training corpus specifically designed to strengthen knowledge- and reasoning-intensive video understanding. It comprises 430K video reasoning examples over 126K newly collected, CC-licensed, expert-domain videos. We develop an expert-in-the-loop, skill-ori…

Cited by 0SourceScholar