做视频理解或多模态模型优化的团队，终于有了一个能大幅降低计算开销而不牺牲性能的方案——AdaCodec用预测式编码直击视频冗余痛点，建议做视频MLLM的开发者直接看论文复现。
视频相邻帧通常高度冗余，但现有视频多模态大模型仍将每帧独立编码为RGB图像，导致大量重复视觉token。AdaCodec提出一种预测式视觉编码接口：仅当场景无法从先前上下文预测时才发送完整参考帧，否则仅传输帧间变化（包括运动和预测残差）作为紧凑的P-token。在11个基准测试中，AdaCodec在相同token预算下优于Qwen3-VL-8B逐帧RGB基线；在长视频基准上，仅用1/7预算（32k token）即超越224k基线，并在通用视频基准上提升平均分数，同时将首token延迟从9.26秒降至1.62秒。
AdaCodec: A Predictive Visual Code for Video MLLMs
Video is temporally redundant: adjacent frames usually share most objects, background, and layout. Yet existing video multimodal large language models (video MLLMs) usually encode each sampled frame as an independent RGB image, causing visual tokens to repeat content already present in earlier frames. This suggests a more direct video interface: send a full reference frame only when the scene cannot be predicted well from prior context, and otherwise transmit a compact description of inter-frame changes. We call this interface a \emph{predictive visual code}, and instantiate it for video MLLMs as \textbf{AdaCodec}. AdaCodec spends full visual tokens on a reference frame only when its conditional predictive cost is high; otherwise, it encodes inter-frame changes, including motion and prediction residuals, as compact P-tokens. Across all eleven benchmarks, AdaCodec improves over the Qwen3-VL-8B per-frame RGB baseline at a matched visual-token budget. Even at $1/7$ the budget, AdaCodec with 32k tokens surpasses the 224k baseline on all long-video benchmarks; on five general-video benchmarks, it raises the average score while substantially cutting time-to-first-token from 9.26s to 1.62s.