VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
This work addresses the lack of training data for knowledge- and reasoning-intensive video understanding, providing a resource and pipeline that improves performance on such tasks.
VideoKR introduces a large-scale training corpus of 315K video reasoning examples over 145K expert-domain videos, designed to enhance knowledge- and reasoning-intensive video understanding. Models post-trained on VideoKR outperform prior approaches on knowledge-intensive video reasoning while remaining competitive on general video reasoning.
We introduce VideoKR, the first large-scale training corpus specifically designed to strengthen knowledge- and reasoning-intensive video understanding. It comprises 315K video reasoning examples over 145K newly collected, CC-licensed, expert-domain videos. We develop a human-in-the-loop, skill-oriented example generation pipeline that targets progressively deeper video reasoning capabilities while ensuring the difficulty, diversity, and reliability of both the examples and their CoT rationales. We also curate VideoKR-Eval, a new expert-annotated benchmark where questions require genuine video understanding and knowledge-intensive reasoning rather than textual shortcuts. Our experiments show that, under a standard SFT$\rightarrow$GRPO pipeline, models post-trained on VideoKR outperform prior post-training approaches on knowledge-intensive video reasoning while remaining competitive on general video reasoning, highlighting data design as a key driver of progress in video reasoning. We further conduct comprehensive ablations to isolate the contributions of VideoKR, providing actionable insights for future work.