AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks

Tengjv Ru, Weitong Lian, Zecong Tang, Lingyi Meng, Haoran Li, Zhejun Cui, Yichen Zhu, Hangshuo Cao, Qi Kang, Yechi Liu, Kaixuan Wang, Yu-Jie Yuan and 3 more

NeurIPS 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Unified any-modality language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Presents VidUEU-Agent, an automated agent pipeline that synthesizes multimodal instruction data from raw videos for understanding, editing, and unified tasks.

Problem

Scarcity and high annotation cost of high-quality multimodal instruction data, while raw videos are abundant but hard to convert into precise instruction data.

Approach

An agent-based automated pipeline that curates instruction data directly from raw videos to cover multimodal understanding, editing, and unified tasks.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on VidUEU-100K understanding dataInternVL3-8B · MMDUscore: 53.1 -> 61.1Improved
fine-tune on VidUEU-100K understanding dataInternVL3-8B · MMEscore: 2308.0 -> 2369.3Improved
fine-tune on VidUEU-100K understanding dataInternVL3-8B · LLaVA-Benchscore: 69.0 -> 70.8No clear effect
fine-tune on VidUEU-100K editing dataBagel · GEdit-Bench-En G_PQscore: 6.831 -> 7.328Improved
fine-tune on VidUEU-100K unified dataBagel · WEAVEbench Overallscore: 0.446 -> 0.501Improved
add autonomous data-distribution iterationVidUEU-Agent · WEAVEbenchscore: 0.448 -> 0.526Improved
update data distribution from iteration 1 to iteration 2VidUEU-Agent · MMDUscore: 29.7 -> 29.2Hurt
add Gate B frame quality filtering (ablation)VidUEU-Agent · GEdit-Bench-En G_Oscore: 5.175 -> 6.951Improved
add the agent pipeline with tool evidence versus fixed-interval VLM QA (ablation)VidUEU-Agent · MMDUscore: 22.0 -> 33.2Improved
add Gate A shot filtering (ablation)VidUEU-Agent · WEAVEbench Overallscore: 0.497 -> 0.501No clear effect
add score-and-similarity greedy keyframe sampling (ablation)VidUEU-Agent · GEdit-Bench-En G_Oscore: 5.848 -> 6.951Improved
add consistency hard rule requiring signal ID citation (ablation)VidUEU-Agent · MMDUscore: 29.4 -> 33.2Improved

Experimental setup

Datasets: raw videos

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