# VideoKR：面向知识与推理密集型视频理解

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-03 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmq0bomkt04pisltr8g9tfqea
- 原文链接：https://arxiv.org/abs/2606.05259

## AI 摘要

VideoKR是首个专为强化知识与推理密集型视频理解设计的大规模训练语料，包含315K个视频推理示例，覆盖145K个新收集的CC许可专家领域视频。研究开发了一种人机协同、面向技能的示例生成管道，并构建了专家标注基准VideoKR-Eval。实验表明，在标准SFT→GRPO流水线下，基于VideoKR后训练的模型在知识密集型视频推理上超越先前方法，同时在通用视频推理上保持竞争力。消融实验进一步证实了数据设计的驱动作用。

## 正文

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 SFTrightarrowGRPO 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.