AI Paper Atlas

Research map / Video / Video generation

UniVBench: Towards Unified Evaluation for Video Foundation Models

Jianhui Wei, Xiaotian Zhang, Yichen Li, Yuan Wang, Yan Zhang, Ziyi Chen, Zhihang Tang, Wei Xu, Zuozhu Liu

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 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
use commercial model Gemini 2.5 Pro versus unified model Showo-2 for video understandingV2T · UniVBench V2Taverage score: 16.3% -> 54.1%Improved
unified model Omni-Video for T2V versus specialist Seedance-1.0-ProT2V · UniVBench T2Vaverage score: 77.9% -> 56.2%Hurt
scale Wan2.1-VACE from 1.5B to 14BV2V reconstruction · UniVBench V2Vaverage score: 34.9% -> 62.7%Improved
reconstruct from model-generated caption instead of ground-truth captionOmni-Video · UniVBenchqualitative consistencyHurt
action dimension versus othersvideo models · UniVBenchdimension score: Action 27.0% vs Color 65.8% (Gemini V2T)Hurt

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