AI Paper Atlas

Research map / Video / Video-language understanding

VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding

Yufei Yin, Qianke Meng, Minghao Chen, Jiajun Ding, Zhenwei Shao, Zhou Yu

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding · 19 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
replace DVD with VideoARM (same o3+GPT-4.1)long-video agent · Video-MME longaccuracy (%): 67.3 -> 75.3Improved
replace DVD with VideoARMlong-video agent · LVBenchaccuracy (%): 76.0 -> 79.7Improved
use VideoARM instead of DVD for token usagelong-video agent · Video-MME (10 videos, 30 queries)tokens: 64.21M -> 1.89MImproved
add Scene Snapper (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 69.0 -> 76.5Improved
add Audio Transcriber (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 70.0 -> 76.5Improved
add Clip Analyzer (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 75.5 -> 76.5Improved
add long-term perception pool (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 67.0 -> 76.5Improved
add short-term perception pool (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 72.5 -> 76.5Improved
add Working Memory (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 75.5 -> 76.5Improved
add HM3 instead of controller context only (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 74.5 -> 76.5Improved
use o3 instead of GPT-4o as controller (ablation)VideoARM · Video-MME long (200-QA subset)accuracy (%): 40.5 -> 76.5Improved
use GPT-4o instead of GPT-4.1 in understanding tools (ablation)VideoARM (o3) · Video-MME long (200-QA subset)accuracy (%): 76.5 -> 80.0Improved

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