WISA: World simulator assistant for physics-aware text-to-video generation

NeurIPSSpotlight2025

Authors
Jing Wang, Ao Ma, Ke Cao, Jun Zheng, Jiasong Feng, Zhanjie Zhang, Wanyuan Pang, Xiaodan Liang
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Recent advances in text-to-video (T2V) generation, exemplified by models such as Sora and Kling, have demonstrated strong potential for constructing world simulators…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

physics video

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive