AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction

Zengjie Chen, Yuxiang Cai, Jingcai Guo, Taotao Cai, Jianwei Yin, Zhi Chen

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Training-free token reduction for MLLMs · 4 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
subtract the prior from posterior (P - Q instead of P) (ablation)token scoring · Scoring ablation, LLaVA-1.5-7B, 64 tokensavg (%): 86.7 -> 87.6Improved
use P log(P/Q) instead of P - Q (ablation)token scoring · Scoring ablation, LLaVA-1.5-7B, 64 tokensavg (%): 87.6 -> 91.5Improved
use P log(P/Q) instead of posterior P (ablation)token scoring · Scoring ablation, LLaVA-1.5-7B, 128 tokensavg (%): 93.7 -> 95.8Improved
use P log(P/Q) instead of posterior P (ablation)token scoring · Scoring ablation, LLaVA-1.5-7B, 32 tokensavg (%): 74.5 -> 84.5Improved
rank by prior Q only instead of posterior P (ablation)token scoring · Scoring ablation, LLaVA-1.5-7B, 64 tokensavg (%): 86.7 -> 79.3Hurt
use entropy score instead of posterior (ablation)token scoring · Scoring ablation, LLaVA-1.5-7B, 64 tokensavg (%): 86.7 -> 72.3Hurt
use log ratio instead of P - Q (ablation)token scoring · Scoring ablation, LLaVA-1.5-7B, 64 tokensavg (%): 87.6 -> 81.7Hurt
add prior correction to FastV-style ranking (ablation)FastV · LLaVA-1.5-7B, 64 tokensnormalized avg (%): 70.7 -> 94.5Improved
add prior correction to FastV-style ranking (ablation)FastV · Qwen3-VL-8B, 11.1% tokensnormalized avg (%): 75.5 -> 87.8Improved
add prior correction to FastV pruning (ablation)FastV · Video-LLaVA video QA (GPT avg acc)accuracy: 26.1 -> 30.7Improved
add prior-guided token merging (ablation)PriorTR pruning · Video-LLaVA video QA (GPT avg acc)accuracy: 30.7 -> 38.7Improved
add prior-guided merging instead of SparseVLM merging (ablation)SparseVLM · Video-LLaVA video QA (Gemini avg acc)accuracy: 40.8 -> 41.6Improved

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