AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

Yuchen Liu, Yaoming Wang, Bowen Shi, Xiaopeng Zhang, Wenrui Dai, Chenglin Li, Hongkai Xiong, Qi Tian

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning · 5 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 post-projection instead of pre-projection fusion (ablation)multi-encoder MLLM · Ablation (558K PT + 1M SFT, EAGLE encoders)average accuracy: 67.5 -> 68.3Improved
use collaborative pruning instead of separate per-encoder pruning (ablation)METEOR · Ablation (558K PT + 1M SFT, EAGLE encoders)average accuracy: 66.9 -> 68.3Improved
use collaborative pruning instead of random pruning (ablation)METEOR · Ablation (558K PT + 1M SFT, EAGLE encoders)average accuracy: 61.4 -> 68.3Improved
use collaborative pruning instead of MLP compression (ablation)METEOR · Ablation (558K PT + 1M SFT, EAGLE encoders)average accuracy: 64.1 -> 68.3Improved
use collaborative pruning instead of Resampler compression (ablation)METEOR · Ablation (558K PT + 1M SFT, EAGLE encoders)average accuracy: 60.3 -> 68.3Improved
use collaborative pruning instead of PixelShuffle (ablation)METEOR · Ablation (558K PT + 1M SFT, EAGLE encoders)average accuracy: 63.9 -> 68.3Improved
add top-k attention head filtering (ablation)text-guided pruning, 297 tokens · Ablation (558K PT + 1M SFT, EAGLE encoders) training-freeOCR average: 59.1 -> 59.9Improved
use instance-adaptive ratio instead of fixed ratio at 242 tokens (ablation)text-guided pruning · Ablation (558K PT + 1M SFT, EAGLE encoders) training-freeaverage accuracy: 66.9 -> 67.9Improved
use instance-adaptive ratio instead of fixed ratio at 242 tokens (ablation)text-guided pruning · Ablation (558K PT + 1M SFT, EAGLE encoders) training-freeOCR average: 62.4 -> 65.0Improved
prune to 126 tokens instead of 242 tokens (ablation)METEOR with adaptive ratio · Ablation (558K PT + 1M SFT, EAGLE encoders) training-freeaverage accuracy: 67.9 -> 67.2Hurt
replace EAGLE with METEOR pruningEAGLE (Vicuna-7B) · Efficient MLLM comparison (EAGLE-based, Vicuna-7B)TFLOPS: 26.21 -> 13.42Improved
replace EAGLE with METEOR pruningEAGLE (Vicuna-7B) · Efficient MLLM comparison (EAGLE-based, Vicuna-7B)average accuracy: 69.3 -> 69.0Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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