AI Paper Atlas

Research map / Video / Video-language understanding

Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence

Jiahao Meng, Xiangtai Li, Haochen Wang, Tan Yue, Tao Zhang, Lingdong Kong, Yunhai Tong, Anran Wang, Zhiyang Teng, Yujing Wang, Zhuochen Wang

ICML 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 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 RL stage after SFT (ablation)Open-o3-Video · V-STARmAM: 28.5 -> 33.7Improved
add SFT cold start before RL (ablation)Open-o3-Video · V-STARmAM: 30.4 -> 33.7Improved
use GSPO instead of GRPO (ablation)SFT+RL · V-STARmAM: 32.8 -> 33.7Improved
add adaptive temporal proximity (ablation)Open-o3-Video reward · V-STARmAM: 33.0 -> 33.7Improved
add temporal gating (ablation)Open-o3-Video reward · V-STARmAM: 32.3 -> 33.7Improved
add spatio-temporal grounded training data (ablation)Open-o3-Video · V-STARmAM: 28.3 -> 33.7Improved
add own annotated data on top of VideoEspresso (ablation)Open-o3-Video · V-STARmAM: 31.1 -> 33.7Improved
adaptive sigma instead of fixed sigma=1.0 (ablation)Open-o3-Video · V-STARmAM: 32.6 -> 33.7Improved
add 30k instead of 15k Video-R1 QA data (ablation)Open-o3-Video · V-STARmAM: 33.7 -> 31.7Hurt
add spatio-temporal evidence (vs text-only reasoning) (ablation)Open-o3-Video · V-STAR mLGMmLGM: 41.0 -> 46.6Improved
remove predicted evidence frames vs random removal (ablation)Open-o3-Video · VideoMME subset (150 questions)accuracy: 66.0 vs 68.0Improved
confidence-aware voting instead of majority votingOpen-o3-Video · WorldSenseaccuracy: 37.3 -> 38.5Improved

Later papers that compared with this method

2 later accepted papers report Open-o3-video-7B as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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