Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
Baiyuan Chen, Shinji Ito, Masaaki Imaizumi
Advances in Neural Information Processing Systems (NeurIPS), 2025
Exploiting Topological Priors for Boosting Point Cloud Generation
Baiyuan Chen
2nd International Conference on Artificial Intelligence, Database and Machine Learning (AIDML), 2024
Advisor: Prof. Tetsuhiro S. Hatakeyama
• A highly selective, research-based course attended by only three students in the department.
• Phase 1: Analyzed various dynamical systems and statistical mechanics models, including chaos, Hodgkin-Huxley
equations, and the Ising model.
• Phase 2: Conducted independent research on traffic congestion and identified unusual patterns in flow-speed relationships.