AI Paper Atlas

Research map / Video / Video-language understanding

VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding

Abdul Waheed, Zhen Wu, Dareen Safar Alharthi, Seungone Kim, Bhiksha Raj

ICLR 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding

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
train judge on bootstrapped data (VideoJudge-3B vs base Qwen2.5-VL-3B)Qwen2.5-VL-3B · VideoJudgeLLaVA-MetaEvalSpearman: 0.63 -> 0.82Improved
train judge on bootstrapped data (VideoJudge-7B vs base Qwen2.5-VL-7B)Qwen2.5-VL-7B · VideoJudgeVCG-MetaEvalSpearman: 0.65 -> 0.74Improved
train judge on bootstrapped data (VideoJudge-3B)Qwen2.5-VL-3B · VideoJudgeVCG-MetaEvalSpearman: 0.51 -> 0.59Mixed
train judge on bootstrapped dataQwen2.5-VL-3B · VATEX-EvalRMSE: 2.27 -> 1.33Improved
enable thinking mode for text-only Qwen3 judges (ablation)Qwen3 (0.6B-4B) · VideoJudgeLLaVA-MetaEvalSpearman: 0.6B: 0.64 -> 0.64; 4B: 0.72 -> 0.68Mixed
use text-only LLM judge with video descriptions instead of video MLLM judge (ablation)Qwen3 vs Qwen2.5-VL judges · Meta-evaluation benchmarksjudging performanceHurt
train judge to generate instance-specific rubrics at test timeQwen2.5-VL-3B · 1000 sampled examples (LLaVA and VCG MetaEval)MAE: 1.15 -> 0.59Improved
add feedback generation to pairwise judging (ablation)Qwen2.5-VL-3B (base) · VideoJudge-Pairwiseaccuracy: 75.00 -> 82.60Improved
add feedback generation to pairwise judging (ablation)VideoJudge-7B · VideoJudge-Pairwiseaccuracy: 98.60 -> 95.60Hurt
increase training max frames up to about 240 (ablation)VideoJudge · Pointwise meta-evaluationcorrelation: correlation exceeds 0.7 up to ~240 framesImproved
increase evaluation max frames beyond 120 (ablation)VideoJudge · Pointwise meta-evaluationcorrelationNo clear effect
raise decoding temperature from 0.0 to 1.0 (ablation)Qwen2.5-VL-3B base · Pointwise meta-evaluationSpearman: 0.56 -> 0.42Hurt

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