{"ID":3084543,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T06:54:00.442624098Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05259","arxiv_id":"2606.05259","title":"VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding","abstract":"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.","short_abstract":"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 generati...","url_abs":"https://arxiv.org/abs/2606.05259","url_pdf":"https://arxiv.org/pdf/2606.05259v1","authors":"[\"Lin Fu\",\"Zheyuan Yang\",\"Yang Wang\",\"Tingyu Song\",\"Arman Cohan\",\"Yilun Zhao\"]","published":"2026-06-03T16:14:20Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}