VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding

• URL: http://arxiv.org/abs/2606.05259v1
• Date: Wed, 03 Jun 2026 16:14:20 GMT
• Title: VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
• Abstract summary: We introduce VideoKR, the first large-scale training corpus specifically designed to strengthen video understanding.<n>VideoKR comprises 315K video reasoning examples over 145K newly collected, CC-licensed, expert-domain videos.<n>We develop a human-in-the-loop, skill-oriented example generation pipeline that targets progressively deeper video reasoning capabilities.
• Score: 52.925648827667935
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Video-ToC: Video Tree-of-Cue Reasoning [65.66891474457466]
  Video Large Language Models (Video LLMs) struggle with complex video understanding.<n>Video-ToC is a novel video reasoning framework that enhances video understanding through tree-of-cue reasoning.
  arXiv  Detail & Related papers  (2026-04-22T12:02:24Z)
• ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models [50.42183477287337]
  Video understanding plays a vital role in bridging low-level visual signals with high-level cognitive reasoning.<n>We introduce a novel video reasoning paradigm: Video-Text Interleaved CoT (ViTCoT)<n>We show that ViTCoT significantly enhances performance compared to the traditional text-only CoT paradigm.
  arXiv  Detail & Related papers  (2025-07-14T03:21:13Z)
• VideoExplorer: Think With Videos For Agentic Long-Video Understanding [117.68219930263153]
  Long-video understanding is a challenging problem in computer vision.<n>We propose VideoExplorer, a framework grounded in the principle of thinking with video''<n>Rather than reasoning over a static context, VideoExplorer iteratively formulates sub-questions, locates relevant moments, and performs task-oriented, temporally scalable video understanding.
  arXiv  Detail & Related papers  (2025-06-12T15:39:10Z)
• Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning [74.1272182814012]
  Video-Skill-CoT (a.k.a. Video-SKoT) is a framework that automatically constructs and leverages skill-aware CoT supervisions for domain-adaptive video reasoning.<n>First, we construct skill-based CoT annotations, cluster them into a shared skill taxonomy, and create detailed multi-step CoT rationale tailored to each video-question pair for training.<n>Second, we introduce a skill-specific expert learning framework. Each expert module specializes in a subset of reasoning skills and is trained with lightweight adapters.
  arXiv  Detail & Related papers  (2025-06-04T03:18:01Z)
• SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge [60.76719375410635]
  We propose a new benchmark (SOK-Bench) consisting of 44K questions and 10K situations with instance-level annotations depicted in the videos. The reasoning process is required to understand and apply situated knowledge and general knowledge for problem-solving. We generate associated question-answer pairs and reasoning processes, finally followed by manual reviews for quality assurance.
  arXiv  Detail & Related papers  (2024-05-15T21:55:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.