AI Paper Atlas

Research map / Video / Video-language understanding

Temporal-Aware Reasoning Optimization for Video Temporal Grounding

Minghang Zheng, Zihao Yin, Yi Yang, Yuxin Peng, Yang Liu

ICML 2026 · Video › Video-language understanding · approach: Temporal video grounding

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 TaRO instead of Time-R1 (Qwen2.5-VL-7B)Time-R1 · Charades-STA, TVGBench zero-shotR1@0.5: 60.8 -> 64.8 (Charades-STA), 29.4 -> 37.8 (TVGBench)Improved
add temporal-sensitive reward alone to the RL baseline (ablation)GRPO baseline · Charades-STA zero-shotR1@0.5: 61.1 -> 63.1Improved
use constructive reasoning exploration alone without the self-exploration phase (ablation)TaRO · Charades-STA zero-shotR1@0.5: 61.1 -> 51.6Hurt
add constructive reasoning exploration with progressive curriculum (ablation)TaRO without temporal reward · Charades-STA zero-shotR1@0.5: 61.1 -> 63.9Improved
add all three components (CRE, TR, PC) (ablation)standard RL baseline · Charades-STA zero-shotR1@0.5: 61.1 -> 64.8Improved
use constructed reasoning with RL-style AW-BC instead of SFT (ablation)CRE warm-up · Charades-STA zero-shotR1@0.5: 63.3 -> 64.8Improved
sample a subset of captions instead of using all captions (ablation)CRE · Charades-STA zero-shotR1@0.5: 63.6 -> 64.8Improved
use AW-BC loss instead of GRPO loss on constructed off-policy rollouts (ablation)CRE warm-up · Charades-STA zero-shotR1@0.5: 46.7 -> 64.8Improved
add advantage weighting and positive-advantage filter to behavioral cloning (ablation)AW-BC loss · Charades-STA zero-shotR1@0.7: 33.7 -> 38.4 (filter), 37.1 -> 38.4 (weighting)Improved
use a weaker open-source captioner (Qwen3.5-4B or 9B) instead of Gemini-3-Pro (ablation)CRE · Charades-STA zero-shotR1@0.5: 64.8 -> 64.2 (9B), 64.3 (4B)No clear effect
shuffle only frames near ground-truth boundaries instead of the full video or random cropping (ablation)temporal-sensitive reward · Charades-STA zero-shotR1@0.5: 63.5 -> 64.8 (full shuffle), 63.1 -> 64.8 (cropping)Improved
lower IoU gate threshold tau to 0.3 or remove gate effect with tau=1.0 (ablation)temporal-sensitive reward · Charades-STA zero-shotR1@0.5: 64.8 -> 61.8 (tau=0.3), 63.9 (tau=1.0)Hurt

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