Hao Wu

Intern, Jarvis Lab, Tencent Jarvis Lab

Joined

February 2023

Names

Hao Wu (Preferred)

Emails

****@mail.ustc.edu.cn (Confirmed)

****@mails.tsinghua.edu.cn (Confirmed)

****@andrew.cmu.edu (Confirmed)

Personal Links

Career & Education History

Intern

Jarvis Lab, Tencent Jarvis Lab (tencent.com)

2025 – Present

Advisors, Relations & Conflicts

Coauthor

Fan Xu

Present

Expertise

Deep Learning

Present

Publications

Equivariant Graph Neural ODEs for Modeling Physical Dynamics
Jiawei Chen, Yuqi Li, Hao Wu, Yueheng Sun, Wenjun Wang
- Submitted to ICLR 2026
- Readers: Everyone
Reinforcing Spatio-Temporal Graph Neural Networks with a Physics Reward Oracle
Hansheng Zeng, Yuqi Li, Chuanguang Yang, Weilun Feng, Zeyu Dong, Yao Lu, Yingli Tian, Hao Wu
- Submitted to ICLR 2026
- Readers: Everyone
Towards Efficient Fairness Image Retrieval with Disentangled Information Suppression
Chuchun Zhang, Wei Ju, Fan Zhang, Hao Wu, QingqingLong, Chong Chen, Xian-Sheng Hua, Yifan Wang
- Submitted to ICLR 2026
- Readers: Everyone
Direct Preference Optimization for Dynamical System Modeling
Hao Wu, Fan Xu, Yuan Gao, Fan Zhang, Kun Wang, Xiaomeng Huang, Qi Song
- Submitted to ICLR 2026
- Readers: Everyone
Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
Hao Wu, Yuan Gao, Fan Xu, Fan Zhang, Qingsong Wen, Kun Wang, Xiaomeng Huang, Xian Wu
- Submitted to ICLR 2026
- Readers: Everyone
VISION: Prompting Ocean Vertical Velocity Reconstruction from Incomplete Observations
Yuan Gao, Hao Wu, Qingsong Wen, Kun Wang, Xian Wu, Xiaomeng Huang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
CAUSAL REASONING WITH LARGE FOUNDATION MOD- ELS TO GUIDE DYNAMIC SYSTEM FORECASTING
Shuaipeng Li, Fan Xu, Xiao Luo, Hao Wu, Ruobing Xie
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Decoding Layer by Layer: Uncovering Hierarchical Reasoning in Language Models
Luo Ji, Yihong Wang, Ningyuan Xi, Yue Zhao, Qingqing Gu, Xiyuan Chen, Hao Wu, Sheng Xu, Hange Zhou, Hongyan Li
- Submitted to ICLR 2026
- Readers: Everyone
Test-Time Safety Alignment with Dynamic Intervention for Jailbreak Defense in LLMs
Shanwen Tan, Wei Ju, Hao Wu, Kun Wang, Yiwei Fu, Yifan Wang, Ziyue Qiao
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models
Hao Wu, Yuan Gao, Xingjian Shi, Shuaipeng Li, Fan Xu, Fan Zhang, Zhihong Zhu, Weiyan Wang, Xiao Luo, Kun Wang, Xian Wu, Xiaomeng Huang
- Submitted to ICLR 2026
- Readers: Everyone

View all 28 publications

Co-Authors

View all 116 co-authors