AI Paper Atlas

Research map / Video / Video-language understanding

Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models

Jinlong Li, Liyuan Jiang, Haonan Zhang, Nicu Sebe

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding · 3 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
add local anchors alongside global anchors (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 56.6 -> 57.0Improved
add global anchors alongside local anchors (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 55.4 -> 57.0Improved
add optimal transport aggregation of pruned tokens (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 56.4 -> 57.0Improved
add intra-frame OT (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 56.3 -> 57.0Improved
add inter-frame OT (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 56.4 -> 57.0Improved
use transport-plan weighting instead of cosine merging (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 52.4 -> 57.0Improved
use transport-plan aggregation instead of no merging (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 56.4 -> 57.0Improved
select anchors by attention instead of randomly (ablation)AOT · Video benchmarks average (ablation, 10% tokens retained)average score: 55.1 -> 57.0Improved
use dynamic clustering frame clips instead of uniform clips (10% retention) (ablation)AOT · Video benchmarks average (LLaVA-OV, 10% tokens retained)average score: 57.0 -> 56.5Hurt
use dynamic clustering frame clips (LLaVA-Video, 25%) (ablation)AOT · Video benchmarks average (LLaVA-Video, 25% tokens retained)average score: 58.2 -> 58.6Improved
raise Sinkhorn iterations from 50 to 100 (ablation)AOT · Sinkhorn-Knopp overheadtime (ms): 2.00 ms -> 2.11 msNo clear effect
AOT vs VisionZip at 10% retention on LLaVA-OVAOT vs VisionZip · Video benchmarks average (LLaVA-OV, 10% tokens retained)average score: 53.5 -> 57.0Improved

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