让视频视觉语言模型学会复用已有信息，大幅降低重复计算开销。
VLMaxxing through FrameMogging Training-Free Anti-Recomputation for Video Vision-Language Models
- 不重新计算稳定视频状态，仅在需要时刷新视觉特征。
- 对同一视频的后续提问延迟降低14.90-35.92倍，准确率保持不变。
- 适合追求推理速度优化的视频多模态应用开发者。
视频视觉语言模型（VLM）常对已知稳定的视觉状态进行重复计算。本文提出无需训练的抗重算策略：当验证确认状态稳定时复用，仅在场景、查询或缓存拓扑变化时获取新证据。在冻结的Qwen2.5-VL-7B-Instruct-4bit模型上，自适应同视频后续复用在93个Query的VideoMME测试中保持配对正确性，同时将后续查询延迟降低14.90–35.92倍。首次查询仍为冷启动，性能提升始于后续复用。压力测试显示，50轮重复提问仍有效；不同修复策略间存在保守与快速漂移的权衡。新鲜视频剪枝效果虽小但真实。C-VISION在首答生成前跳过定时视觉塔计算，在Gemma 4-E4B-4bit上实现32帧短序列1.316倍首查询加速，20项测试无配对漂移或解析失败。阶段共享上限（C-CEILING）确保组件加速仅按实际耗时占比转化为端到端加速，避免夸大。候选C-STREAM仍为原生速率目标，非本工作重点。更广泛方向是构建原生支持变化、运动、不确定性、对象状态、传感器时间与激活区域的视频媒体，使模型无需每帧从密集RGB重新发现世界。
原文摘要 · Abstract (English)
Video vision-language models (VLMs) keep paying for visual state the stream already told us was stable. The factory wall did not move, but most VLM pipelines still hand the model dense RGB frames or a fresh prefix again. We study that waste as training-free anti-recomputation: reuse state when validation says it survives, and buy fresh evidence when the scene, query, or cache topology requires it. The largest measured win is after ingest. On frozen Qwen2.5-VL-7B-Instruct-4bit, adaptive same-video follow-up reuse preserves paired choices and correctness on a 93-query VideoMME breadth setting while reducing follow-up latency by 14.90-35.92x. The first query is still cold; the win starts when later questions reuse the same video state. Stress tests bound the result: repeated-question schedules hold through 50 turns, while dense-answer-anchored prompt variation separates conservative fixed K=1 repair from faster aggressive policies that drift. Fresh-video pruning is smaller but real. C-VISION skips timed vision-tower work before the first answer is generated. On Gemma 4-E4B-4bit, the clean 32f short cell reaches 1.316x first-query speedup with no paired drift or parse failures on 20 items; Qwen shows the fidelity/speed boundary. Stage-share ceiling (C-CEILING) is the accounting guardrail: a component speedup becomes an end-to-end speedup only in proportion to the wall-clock share it accelerates, so C-VISION and after-ingest follow-up reuse do not multiply. Candidate C-STREAM remains a native-rate target, not a headline result here. The broader direction is VLM-native media that expose change, motion, uncertainty, object state, sensor time, and active tiles directly, so models do not have to rediscover the world from dense RGB every frame.
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。