MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference

NeurIPSSpotlight2025

Authors: Haibo Tong, Zhaoyang Wang, Zhaorun Chen, Haonian Ji, Shi Qiu, Siwei Han, Kexin Geng, Zhongkai Xue, Yiyang Zhou, Peng Xia, Mingyu Ding, Rafael Rafailov, Chelsea Finn, Huaxiu Yao
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

benchmark video

← All NeurIPS 2025 Spotlight papers · Browse the whole archive