Publications

I am broadly interested in both the theoretical limits and empirical applications of reinforcement learning and online learning (e.g., multi-armed bandits), with a current focus on designing practical algorithms with provable guarantees for LLMs. Feel free to reach out if you share similar interests!

Conferences

SP²ec: Adaptive Self-Speculative Decoding for Vision-Language Models

Yuqi Huang, Xingyao Li, Yunlong Hou, Fengzhuo Zhang, Jiachun Pan and Vincent Y. F. Tan.
Conference on Neural Information Processing Systems (NeurIPS), 2026.

TL;DR: We exploit the single-peak structure in self-speculative decoding to further boost the inference speed.

Rethinking ''RL Generalizes, SFT Memorizes'': The Role of SFT Data

Yunlong Hou, Fengzhuo Zhang, Yuan Cheng, Jiachun Pan, Xingyao Li and Zhuoran Yang.
Conference on Neural Information Processing Systems (NeurIPS), 2026; The first Foundations of Deep Generative Models workshop, ICML 2026; 2026 INFORMS Annual Meeting.

TL;DR: We revisit the generalization ability of SFT and RL training from the data perspective.

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms

Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan and Zhuoran Yang.
International Conference on Machine Learning (ICML), 2025

TL;DR: A training-free approach to adaptively select the draft hyperparameter to improve inference efficiency.

Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits

Yunlong Hou, Vincent Y. F. Tan and Zixin Zhong.
Conference on Neural Information Processing Systems (NeurIPS), 2024

TL;DR: Best Arm Identification under the piecewise-stationary environment, where the best arm has the best average performance.

Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits

Yunlong Hou, Vincent Y. F. Tan and Zixin Zhong.
International Conference on Machine Learning (ICML), 2023

TL;DR: Regret minimization with any-time risk constraint.

Journals

Bayesian Best-Arm Identification with Abstention: A Polynomial-to-Exponential Phase Transition

Yuqi Huang, Yunlong Hou and Vincent Y. F. Tan.
Under Review

TL;DR: Fixed-budget BAI in the Bayesian setting, with the option of abstention at the end of the sampling process.

On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits

Yunlong Hou, Zixin Zhong and Vincent Y. F. Tan.
Under review; European Workshop on Reinforcement Learning (EWRL), 2026.

TL;DR: Regret Minimization with a free exploration time period at the front.

Demystifying the Slash Pattern in Attention: The Role of RoPE

Yuan Cheng, Fengzhuo Zhang, Yunlong Hou, Cunxiao Du, Chao Du, Tianyu Tang, Aixin Sun and Zhuoran Yang.
Under review; The first Foundations of Deep Generative Models workshop, ICML 2026

TL;DR: The slash pattern in attention is caused by RoPE.

Almost Optimal Variance-Constrained Best Arm Identification

Yunlong Hou, Vincent Y. F. Tan and Zixin Zhong.
IEEE Transactions on Information Theory (IEEE TIT), Volume 69, Issue 4, April 2023, doi: 10.1109/TIT.2022.3222231.

TL;DR: Best Arm Identification with risk constraint (e.g., variance).