Selected Publications

For a complete list, please refer to my Google Scholar profile. The publications are listed reverse chronologically.

* indicates equal contribution.

Preprints

arXiv2026
One Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices
Ruishuo Chen, Weijia Li, Xun Wang, Yu Chen, Leheng Cai, and Longbo Huang.
arXiv preprint, 2026.
arXiv
arXiv2026
The Router Within: Eliciting Native Skill Routing from a Frozen LLM
Ruishuo Chen, Xun Wang, Yu Chen, Zhuoran Li, and Longbo Huang.
arXiv preprint, 2026.
arXiv
arXiv2026
Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees
Yu Chen*, Ruishuo Chen*, Xun Wang, Zhuoran Li, and Longbo Huang.
arXiv preprint, 2026.
arXiv
arXiv2026
When Context Returns: Toward Robust Internalization in On-Policy Distillation
Xun Wang, Ruishuo Chen, Zhuoran Li, Yu Chen, and Longbo Huang.
arXiv preprint, 2026.
arXiv

Publications

UAI2026
On the Sublinear Regret of Continuous K-Max Bandits
Yu Chen*, Siwei Wang*, Longbo Huang, and Wei Chen.
Forty-second Conference on Uncertainty in Artificial Intelligence, 2026.
Proceedings arXiv
ICML2026
Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
Yu Chen, Yuhao Liu, Jiatai Huang, Yihan Du, and Longbo Huang.
Forty-third International Conference on Machine Learning, 2026.
OpenReview arXiv
ICML2026
PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
Ruishuo Chen, Yu Chen, Zhuoran Li, and Longbo Huang.
Forty-third International Conference on Machine Learning, 2026.
OpenReview arXiv Code
ICML2026
Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
Rui Hu, Yu Chen, and Longbo Huang.
Forty-third International Conference on Machine Learning, 2026.
OpenReview arXiv
ICLR2026
Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
Yuhao Liu, Yu Chen, Rui Hu, and Longbo Huang.
The Fourteenth International Conference on Learning Representations, 2026.
Proceedings arXiv
ICML2025
Finite-Time Analysis of Discrete-Time Stochastic Interpolants
Yuhao Liu, Yu Chen, Rui Hu, and Longbo Huang.
Forty-second International Conference on Machine Learning, 2025.
Proceedings arXiv
ICLR2025
uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
Yu Chen*, Jiatai Huang*, Yan Dai*, and Longbo Huang.
The Thirteenth International Conference on Learning Representations, 2025. Spotlight, Top 5%
Proceedings arXiv
ICML2024
Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
Yu Chen*, Xiangcheng Zhang*, Siwei Wang, and Longbo Huang.
Forty-first International Conference on Machine Learning, 2024.
Proceedings arXiv
ICML2024
Provably Efficient Partially Observable Risk-Sensitive Reinforcement Learning with Hindsight Observation
Tonghe Zhang*, Yu Chen*, and Longbo Huang.
Forty-first International Conference on Machine Learning, 2024.
Proceedings arXiv
TON2024
Multi-User Delay-Constrained Scheduling With Deep Recurrent Reinforcement Learning
Pihe Hu, Yu Chen, Ling Pan, Zhixuan Fang, Fu Xiao, and Longbo Huang.
IEEE/ACM Transactions on Networking, 2024.
Journal
ICLR2024
Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback
Yu Chen, Yihan Du, Pihe Hu, Siwei Wang, Desheng Wu, and Longbo Huang.
The Twelfth International Conference on Learning Representations, 2024.
Proceedings arXiv
ICLR2023
Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs
Pihe Hu*, Yu Chen*, and Longbo Huang.
The Eleventh International Conference on Learning Representations, 2023.
OpenReview
MobiHoc2022
Effective multi-user delay-constrained scheduling with deep recurrent reinforcement learning
Pihe Hu, Ling Pan, Yu Chen, Zhixuan Fang, and Longbo Huang.
Twenty-third International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, 2022.
Proceedings arXiv
ICML2022
Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Pihe Hu, Yu Chen, and Longbo Huang.
Thirty-ninth International Conference on Machine Learning, 2022.
Proceedings arXiv