ReFoCUS: 用于上下文理解的强化引导帧优化
ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding
AI总结：
提出ReFoCUS框架，首次将在线策略梯度强化学习集成到视频大语言模型的帧级优化中，通过自回归和查询条件选择架构学习帧选择策略，无需显式帧级监督，提升视频问答推理准确性。
摘要：
近期大型多模态模型（LMMs）的进展实现了有效的视觉-语言推理，然而视频理解能力仍受限于次优的帧选择策略，尽管视频专用LMMs发展迅速。先前的工作尝试通过静态启发式或外部检索模块来提供帧级信息，但这些方法往往无法捕捉与给定用户查询相关的视觉线索，混淆了原始视觉动态与真正的语义相关性。在本文中，我们介绍了ReFoCUS（用于上下文理解的强化引导帧优化），这是首个将在线策略梯度强化学习集成到视频-LLMs帧级优化的框架。ReFoCUS旨在学习帧选择策略，利用来自参考模型的奖励信号来捕捉其对最佳支持时间接地响应的帧组合的潜在评分行为。为了高效探索巨大的组合帧空间，我们采用了一种自回归且查询条件的选择架构，确保上下文一致性的同时降低复杂度。我们的策略学习无需显式帧级监督，因为它隐式地发现了最优且语义一致的帧组合。ReFoCUS在多个视频问答基准测试中持续提高了推理准确性，证明了将帧选择与模型内部效用对齐的优势。
英文摘要：
Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs. Prior works attempted to solve this with static heuristics or external retrieval modules to feed frame-level information, but these approaches often fail to capture visual cues grounded to the given user queries conflating raw visual dynamics with true semantic relevance. In this paper, we introduce ReFoCUS (Reinforcement-guided Frame Optimization for Contextual UnderStanding), the first framework to integrate online policy-gradient reinforcement learning into frame-level optimization for video-LLMs. ReFoCUS aims to learn a frame selection policy, leveraging reward signals derived from reference models to capture their underlying scoring behavior over frame combinations that best support temporally grounded responses. To efficiently explore the large combinatorial frame space, we employ an autoregressive and query-conditional selection architecture that ensures contextual consistency while reducing complexity. Our policy learning removes the need for explicit frame-level supervision, as it implicitly discovers optimal and semantically consistent frame compositions. ReFoCUS consistently improves reasoning accuracy across multiple video QA benchmarks, demonstrating the advantage of aligning frame selection with model-internal utility.
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。
