Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
Jul 1, 2026·,,
,,,,,,·
1 min read
J Meng
X Li
H Wang
Yue Tan
T Zhang
L Kong
Y Tong
A Wang
Z Teng
et al.
Type
Publication
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026)
Status
Peer-reviewed
Open access
This publication entry was migrated from the previous site.
Citation: J Meng, X Li, H Wang, Yue Tan, T Zhang, L Kong, Y Tong, A Wang, Z Teng, et al. (2026). “Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence.” ICML 2026.
Authors
My name is Yue Tan, and you can also call me Tangent. I am a 2022
undergraduate student at the School of Information Science and Technology,
Peking University, and a 2026 Ph.D. student at the School of Computer Science,
Peking University. My research interests include video understanding,
post-training of multimodal large models, image generation and editing, and
video generation.