Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior

Yulin Li, Haokun GUI, Ziyang Fan, Junjie Wang, Bin Kang, BIN CHEN, Zhuotao Tian

Keywords: Efficient Large Multimodal Models, Video Large Language Models, Token Pruning

Abstract: Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long videos. While existing keyframe sampling methods can improve temporal modeling efficiency, additional computational cost is introduced before feature encoding, and the binary frame selection paradigm is found suboptimal. Therefore, in this work, we propose **Dy**namic **To**ken compression via LLM-guided **K**eyframe prior (**DyToK**), a training-free paradigm that enables dynamic token compression by harnessing VLLMs' inherent attention mechanisms. Our analysis reveals that VLLM attention layers naturally encoding query-conditioned keyframe priors, by which DyToK dynamically adjusts per-frame token retention ratios, prioritizing semantically rich frames while suppressing redundancies. Extensive experiments demonstrate that DyToK achieves state-of-the-art efficiency-accuracy tradeoffs. DyToK shows plug-and-play compatibility with existing compression methods, such as VisionZip and FastV, attaining 2.5x faster inference while preserving accuracy across multiple VLLMs, such as LLaVA-OneVision and Qwen2.5-VL. Code and models will be made publicly available.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 19575