Publications

Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
Rui Hu, Yu Chen, Longbo Huang
Forty-Third International Conference on Machine Learning [ICML], 2026. [PDF]

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks
Rui Hu*, Yifan Zhang*, Zhuoran Li, Longbo Huang
The Thirteenth International Conference on Learning Representation [ICLR], 2025. (Spotlight, Top 5%) [PDF]

Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
Ruishuo Chen, Xun Wang, Rui Hu, Zhuoran Li, Longbo Huang
Forty-Third International Conference on Machine Learning [ICML], 2026. [PDF]

Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
Yuhao Liu, Rui Hu, Yu Chen, Longbo Huang
The Fourteenth International Conference on Learning Representation [ICLR], 2026. [PDF]

Finite-Time Analysis of Discrete-Time Stochastic Interpolants
Yuhao Liu, Yu Chen, Rui Hu, Longbo Huang
Forty-Second International Conference on Machine Learning [ICML], 2025. [PDF]