Video-Zero: 自主进化视频理解
Video-Zero: Self-Evolution Video Understanding
AI总结：
本文提出Video-Zero框架，通过无标注的Questioner-Solver共进化机制，聚焦时间局部证据，提升视频理解的自进化能力，验证了证据中心自进化方法的有效性与迁移性。
摘要：
自我进化提供了一种无需依赖密集人工标注的提升推理模型的有前景路径。然而，将这一范式扩展到视频理解仍处于探索和挑战之中：视频是长的、动态的和冗余的，而推理所需证据往往是稀疏且时间局部化的。简单地从完整视频中生成困难的问题-答案对因此会产生看似具有挑战性但基础薄弱的监督，依赖于静态线索或语言先验，而非时间证据。在本文中，我们主张视频自我进化的主要瓶颈并非难度本身，而是证据的 grounding。我们提出了 Video-Zero，一个无需标注的 Questioner--Solver 共进化框架，该框架以时间局部化的证据为中心。Questioner 发现信息丰富的证据片段并生成证据基础的问题，而 Solver 学会回答并使其预测与支持证据对齐。这关闭了证据发现、证据基础监督和证据对齐学习的迭代循环。在涵盖时间定位、长视频理解和视频推理的13个基准上，Video-Zero 一致提升了多个视频 VLM 基础架构，证明了以证据为中心的自我进化有效性和可迁移性。
英文摘要：
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains underexplored and challenging: videos are long, dynamic, and redundant, while the evidence needed for reasoning is often sparse and temporally localized. Naively generating difficult question-answer pairs from full videos can therefore produce supervision that appears challenging but is weakly grounded, relying on static cues or language priors rather than temporal evidence. In this work, we argue that the key bottleneck of video self-evolution is not difficulty alone, but grounding. We propose Video-Zero, an annotation-free Questioner--Solver co-evolution framework that centers self-evolution on temporally localized evidence. The Questioner discovers informative evidence segments and generates evidence-grounded questions, while the Solver learns to answer and align its predictions with the supporting evidence. This closes an iterative loop of evidence discovery, grounded supervision, and evidence-aligned learning. Across 13 benchmarks spanning temporal grounding, long-video understanding, and video reasoning, Video-Zero consistently improves multiple video VLM backbones, demonstrating the effectiveness and transferability of evidence-centered self-evolution.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
