AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM

Han Wang, Yuxiang Nie, Yongjie Ye, Yanjie Wang, Shuai Li, Haiyang Yu, Jinghui Lu, Can Huang

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adaptive pooling instead of token pruning as the dynamic compressor (ablation)Dynamic-VLM · VideoMME (w/o subtitles)accuracy: 47.6% -> 52.0%Improved
use adaptive pooling instead of token merging as the dynamic compressor (ablation)Dynamic-VLM · VideoMME (w/o subtitles)accuracy: 51.6% -> 52.0%Improved
use adaptive pooling instead of token pruning (ablation)Dynamic-VLM · MSVD-QAaccuracy: 59.5 -> 62.0Improved
use adaptive pooling instead of token merging (ablation)Dynamic-VLM · MSVD-QAaccuracy: 61.9 -> 62.0No clear effect
raise tokens per frame from 36 to 100 at 12000 max tokens (ablation)Dynamic-VLM 7B · VideoMME (w/o subtitles)accuracy: 58.7% -> 60.9%Improved
raise tokens per frame from 100 to 256 at 12000 max tokens (ablation)Dynamic-VLM 7B · VideoMME (w/o subtitles)accuracy: 60.9% -> 59.3%Hurt
raise max visual tokens from 4000 to 12000 at 100 tokens per frame (ablation)Dynamic-VLM 7B · VideoMME (w/o subtitles)accuracy: 58.2% -> 60.9%Improved
raise max visual tokens from 8000 to 12000 at 36 tokens per frame (more frames, 222 to 333) (ablation)Dynamic-VLM 7B · VideoMME (w/o subtitles)accuracy: 59.3% -> 58.7%No clear effect
train on the proposed 2M synthetic video QA data with dynamic compression, compared with LLaVA-OneVision 7BDynamic-VLM 7B · VideoMME (w/o subtitles)accuracy: 58.2% -> 60.9%Improved
same comparison on zero-shot multi-image QA with video-only trainingDynamic-VLM 7B · MuirBenchaccuracy: 41.8% -> 50.7%Improved
scale LLM from 7B to 14BDynamic-VLM · VideoMME (w/o subtitles)accuracy: 60.9% -> 64.6%Improved
scale LLM from 7B to 14BDynamic-VLM · MMIUaccuracy: 43.7% -> 51.7%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy