AI Paper Atlas

Research map / Video / Video-language understanding

Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding

Linghao Meng, Qiankun Li, Junyuan Mao, Pujin Liao, Zhicheng He, Enbo Zhang, Kun Wang, Yang Liu, Huazhu Fu, Yueming Jin

ECCV 2026 · Video › Video-language understanding · approach: Long video understanding · 0 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 entity extraction (EE) (ablation)ReMem on LLaVA-Video · LVBenchaccuracy: 52.3 -> 54.5Improved
add entity extraction (EE) (ablation)ReMem on LLaVA-Video · MLVUaccuracy: 75.8 -> 77.3Improved
add static visual-semantic alignment (VSA) (ablation)ReMem on LLaVA-Video · LVBenchaccuracy: 41.6 -> 54.5Improved
add static visual-semantic alignment (VSA) (ablation)ReMem on LLaVA-Video · MLVUaccuracy: 64.0 -> 77.3Improved
add memory temporal-semantic alignment (TSA) (ablation)ReMem on LLaVA-Video · LVBenchaccuracy: 47.6 -> 54.5Improved
add memory temporal-semantic alignment (TSA) (ablation)ReMem on Qwen2-VL · LVBenchaccuracy: +7.3%Improved
add structure-aware frame routing (FR) instead of Top-K (ablation)ReMem on LLaVA-Video · Video-MMEaccuracy: 62.3 -> 69.2Improved
add frame routing (FR) instead of Top-K (ablation)ReMem on Qwen2-VL · MLVUaccuracy: +6.8%Improved
add static visual-semantic alignment (VSA) (ablation)ReMem on Qwen2-VL · LVBenchaccuracy: +12.3%Improved
continuous granularity weighting instead of binary alpha (0.9/0.5) (ablation)ReMem on Qwen2-VL · LongVideoBenchaccuracy: +3.3%Improved
candidate pool N 150 instead of 90 (ablation)ReMem on LLaVA-Video · Video-MMEaccuracy: 65.5 -> 69.2Improved
enlarge candidate pool N from 150 to 200ReMem on LLaVA-Video · Video-MMEaccuracy: 69.2 -> 68.9Hurt

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