Author

Haoxuan Li

Observed name: Li, Haoxuan

Institutions: Peking University, Huazhong University of Science and Technology

Observed institutions: Peking University, Huazhong University of Science and Technology

OpenAlex ID: A5158742420

RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution

2026 · Zhang, Fan, Wu, Hao, et al. · arXiv (Cornell University) · 2

Matching Complexity for Second-Order Stationary Point with Sample Reuse

2026 · Chen, Qian, Wu, Wendao, et al. · arXiv (Cornell University) · 1

Matching Randomized Bounds for Finite-Sum Nonconvex-Concave Optimization

2026 · Wu, Wendao, Zhang, Haihan, et al. · arXiv (Cornell University) · 1

DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving

2026 · Wang, Shuzheng, Li, Haoxuan, et al. · arXiv (Cornell University)

Matching Full-Hessian Oracle Complexity for Nonconvex--Strongly-Concave Minimax Optimization

2026 · Zhang, Fangqing, Zhang, Haihan, et al. · arXiv (Cornell University)

Matching Randomized First-Order Bounds for Higher-Order Smooth Nonconvex Optimization

2026 · Zhang, Haihan, Wu, Wendao, et al. · arXiv (Cornell University)

Works count: 6

Citation count: 4

H-index: 1

I10-index: