让视频理解模型按需压缩，关键帧保细节，无关帧大幅删减。
VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
- 双路由机制：语义路由选压缩策略，图像路由评帧重要性。
- 在多个数据集上实现最高67.9%的视觉令牌压缩，性能不降。
- 适合长视频理解、资源受限场景下的高效多模态应用。
视频大模型在处理长视频时面临可扩展性瓶颈：长视频产生过长的视觉标记序列，显著增加推理时的内存与延迟。现有压缩方法虽在特定场景有效，但多数缺乏强查询感知能力，或对所有帧采用固定压缩策略，难以应对视觉证据时间分布不均的问题。为此，我们提出VideoRouter，一个基于InternVL的查询自适应双路由框架，实现预算约束下的证据精准分配。语义路由预测主导压缩策略，选择广覆盖时间范围或自适应高分辨率保留；图像路由利用早期LLM层评分帧相关性，实现对不相关帧的激进压缩，同时保留关键证据帧的细节。为训练双路由，我们构建了Video-QTR-10K用于分配策略监督，以及Video-FLR-200K用于帧相关性监督。在VideoMME、MLVU和LongVideoBench上的实验表明，VideoRouter在相同或更低预算下持续优于InternVL基线，最高实现67.9%的令牌减少。
原文摘要 · Abstract (English)
Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long visual-token sequences, which sharply increase memory and latency during inference. While existing compression methods are effective in specific settings, most are either weakly query-aware or apply a fixed compression policy across frames, proving suboptimal when visual evidence is unevenly distributed over time. To address this, we present VideoRouter, a query-adaptive dual-router framework built on InternVL for budgeted evidence allocation. The Semantic Router predicts the dominant allocation policy, choosing between broad temporal coverage and adaptive high-resolution preservation, while the Image Router uses early LLM layers to score frame relevance. This enables aggressive compression on less relevant frames while preserving detail on critical evidence frames. To train both routers, we build Video-QTR-10K for allocation-policy supervision and Video-FLR-200K for frame-relevance supervision. Experiments on VideoMME, MLVU, and LongVideoBench show that VideoRouter consistently improves over the InternVL baseline under comparable or lower budgets, achieving up to a 67.9% token reduction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。