I am a senior algorithm engineer with Qwen Unit, Alibaba Group, where I focus on reinforcement learning for language models with a strong drive toward real-world applications.

Before this, I worked at Ant Group, where I focused on doing LLM-RL research and its application in the safety post-training stage of the company’s foundation models.

Before that, I did my Ph.D. in Dr. Tianyi Chen’s group which I was fortunate to join as the first Ph.D. student. My Ph.D. research focused on optimization and reinforcement learning. Meanwhile, I was a research intern with IBM Research AI where I collaborated with Pin-Yu Chen, Payel Das, Songtao Lu, Xiaodong Cui and many other talented researchers. My research at IBM focused on LLM alignment and RL.

News and highlights

• [Jul. 2026] I joined the Qwen Bussiness Unit of Alibaba Group, where I will be working on the LLM-RL foundational algorithms.
• [May. 2026] One co-authored paper accepted in ICML 2026.
• [Jan. 2026] Our paper on entropy regularization of LLM-RL is accepted in ICLR 2026.
  • On Entropy Control in LLM-RL Algorithms
• [Mar. 2025] I am excited to join Ant Group via its research talent program Ant Star.
• [Feb. 2025] The extended study of our ICML 2024 paper is accepted in JMLR.
  • ArXiv: Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
• [Jan. 2025] Our paper is accepted in ICLR 2025:
  • SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
• [Dec. 2024] An extended study of our ICML 2023 paper has been accepted in Mathematical Programming.
  • On Penalty-based Bilevel Gradient Descent Method
• [Oct. 2024] New paper on improved LLM alignment framwork:
  • Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning

Industry experiences

Qwen Unit, Alibaba Group. Present

• Senior foundational algorithm engineer.

Ant Group. 03.2025 - 07.2026

• Senior research engineer, joined via Ant Star talent program.

IBM Research AI, T. J. Watson Research Center. 05.2024 - 08.2024

• Research intern, mentored by Dr. Pin-Yu Chen and Dr. Payel Das.

IBM Research AI, T. J. Watson Research Center. 05.2021 - 08.2021

• Research intern, mentored by Dr. Songtao Lu and Dr. Xiaodong Cui.

Selected research

• On Entropy Control in LLM-RL Algorithms
  Han Shen
  ICLR 2026. [paper]

• SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
  Han Shen, Pin-Yu Chen, Payel Das, Tianyi Chen
  ICLR 2025. [paper]

• Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
  Han Shen, Zhuoran Yang, Tianyi Chen
  ICML 2024, extended work in JMLR [paper]

• Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
  Heshan D. Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen
  ICLR 2023 Oral. [paper]

• On Penalty-based Bilevel Gradient Descent Method
  Han Shen, Quan Xiao, Tianyi Chen
  ICML 2023, extended work in Mathematical Programming. [paper]

• A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences
  Han Shen, Tianyi Chen
  NeurIPS 2022 Oral. [paper]

Services

Reviewer for NeurIPS, ICML, ICLR, AISTATS, AAAI, IEEE Transactions on Signal Processing, etc.