AI Paper Atlas

Research map / Video / Video-language understanding

LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding

Jihao Qiu, Lingxi Xie, Xinyue Huo, Qi Tian, Qixiang Ye

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding · 8 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 RL with GRPO after SFT (full data) (ablation)LongVideo-R1 Qwen3-8B · LVBenchaccuracy: 41.6 -> 50.0Improved
increase SFT data from 10K to full 33K samples (after RL) (ablation)LongVideo-R1 · LVBenchaccuracy: 47.4 -> 50.0Improved
increase SFT data from 10K to full (SFT only) (ablation)LongVideo-R1-SFT · LVBenchaccuracy: 39.1 -> 41.6Improved
add location reward r_loc in RL (ablation)LongVideo-R1 · LVBenchaccuracy: 45.8 -> 50.0Improved
add location reward r_loc in RL (ablation)LongVideo-R1 · Video-MME longaccuracy: 61.4 -> 64.4Improved
add location reward r_loc in RL (ablation)LongVideo-R1 · LVBench temporal groundingaccuracy: 53.2 -> 56.4Improved
scale captioning MLLM from 3B to 72B (ablation)LongVideo-R1 · LVBenchaccuracy: 44.5 -> 50.0Improved
scale captioning MLLM from 32B to 72B (ablation)LongVideo-R1 · LVBenchaccuracy: 49.8 -> 50.0No clear effect
increase maximum tool rounds from 10 to 30 (ablation)LongVideo-R1 · LVBenchaccuracy: 43.0 -> 50.0Improved
increase maximum tool rounds from 20 to 30 (ablation)LongVideo-R1 · LVBenchaccuracy: 47.3 -> 50.0Improved
use Qwen3-VL-32B captions and renewed SFT dataLongVideo-R1 · LVBenchaccuracy: 50.0 -> 60.7Improved
use Qwen3-VL-32B captions and renewed SFT dataLongVideo-R1 · MLVUaccuracy: 68.1 -> 71.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 5 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