AI Paper Atlas

Research map / Video / Video-language understanding

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

Yuan Xie, Tianshui Chen, Zheng Ge, Lionel Ni

ICML 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
use multi-turn retrieval reasoning instead of single-turn with uniformly sampled frames (ablation)Video-MTR (Qwen2.5-VL-7B, 80 frames) · LVBenchaccuracy: 35.3 -> 42.3Improved
use multi-turn retrieval reasoning instead of single-turn (ablation)Video-MTR (Qwen2.5-VL-7B, 80 frames) · VideoMME (w/o sub.) overallaccuracy: 57.2 -> 62.7Improved
add turn-level frame-relevance reward (bi-level reward) (ablation)Video-MTR multi-turn · LVBenchaccuracy: 37.7 -> 42.3Improved
add turn-level frame-relevance reward (bi-level reward) (ablation)Video-MTR multi-turn · VideoMME (w/o sub.) overallaccuracy: 58.3 -> 62.7Improved
gate turn-level rewards on final answer correctness (ablation)Video-MTR · training dynamicsQA accuracy and number of turnsImproved
apply Video-MTR RL training to Qwen2.5-VL-7B at same frame budgetQwen2.5-VL-7B, 80 frames · LVBenchaccuracy: 33.6 -> 42.3Improved
apply Video-MTR RL training to Qwen2.5-VL-7B at same frame budgetQwen2.5-VL-7B, 80 frames · EgoSchema (Subset)accuracy: 63.5 -> 68.8Improved
increase frame budget from 32 to 80Video-MTR · VideoMME (w/o sub.)accuracy: 59.0 -> 62.7Improved
multi-turn reasoning on long videos versus short videosVideo-MTR vs Qwen2.5-VL-7B, 32 frames · VideoMME (w/o sub.)accuracy gain: Short +4.6, Medium +5.3, Long +6.3Improved
multi-turn reasoning on holistic versus detail tasksVideo-MTR vs Qwen2.5-VL-7B · MLVUaccuracy gain: holistic +3.8%, single-detail +7.5%, multi-detail +8.1%Improved
multi-turn RL with Video-MTR still lags large proprietary model on some benchmarksVideo-MTR 80 frames · VideoMME (w/o sub.)accuracy: 62.7 vs GPT-4o 71.9No clear effect

Later papers that compared with this method

3 later accepted papers report Video-MTR as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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