VideoKR：面向知识与推理密集型的视频理解

摘要

我们提出VideoKR，这是首个专门用于增强知识与推理密集型视频理解能力的大规模训练语料库。该语料库包含31.5万个视频推理示例，涵盖14.5万个新收集的、采用CC许可协议的专家领域视频。我们开发了一种人在回路中、面向技能的示例生成流程，该流程针对渐进式加深视频推理能力进行设计，同时确保示例及其思维链推理过程的难度、多样性和可靠性。我们还构建了VideoKR-Eval基准，这是一个经专家标注的新基准，其问题要求基于真实的视频理解与知识密集型推理，而非依赖文本捷径。实验表明，在标准SFT→GRPO训练流程下，基于VideoKR进行后训练的模型在知识密集型视频推理任务上优于此前所有后训练方法，同时在通用视频推理任务上保持竞争力，这凸显了数据设计作为视频推理进步关键驱动因素的价值。我们进一步开展了全面的消融实验，以分离VideoKR的贡献，为未来研究提供可操作的指导。

English

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.