Eric Hanchen Jiang

Eric Hanchen Jiang

πŸ‘‹ Hi!

My name is Eric Jiang (ε§œζ±‰ζ™¨), and I am an first year Statistics and Data Science PhD student at UCLA, supervised by Prof. Kai-Wei Chang and Prof. Yingnian Wu.

πŸ”Ž Current Research Topics

  • Reinforcement Learning: Robust RL, offline/online RL, In-Context Learning
  • Large Language Models: RLHF, Safety, Agentic AI

πŸ”₯ News

  • 2025.11: Β πŸŽ‰πŸŽ‰ Two papers Accepted to AAAI 2026
  • 2025.09: Β πŸŽ‰πŸŽ‰ One paper Accepted to NeurIPS 2025
  • 2025.06: Β πŸŽ‰πŸŽ‰ I graduated from University of California, Los Angeles with double degrees in Math of Computation and Statistics and Data Science
  • 2025.01: Β πŸŽ‰πŸŽ‰ I received the Graduate Dean’s Scholar Award (GDSA), awarded to the top 2 UCLA Statistics and Data Science PhD applicants (Top 1%).

πŸ“ Publications

Preprint
sym

Energy-Driven Steering: Reducing False Refusals in Large Language Models

Eric Hanchen Jiang†, Weixuan Ou†, Run Liu, Shengyuan Pang, Guancheng Wan, Ranjie Duan, Wei Dong, Kai-Wei Chang, XF Wang, Ying Nian Wu, Xinfeng Li

Code

Preprint
sym

Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models

Eric Hanchen Jiang†, Guancheng Wan†, Sophia Yin†, Mengting Li†, Yuchen Wu, Xiao Liang, Xinfeng Li, Yizhou Sun, Wei Wang, Kai-Wei Chang, Ying Nian Wu

Code

Preprint
sym

Learning to Rank Chain-of-Thought: An Energy-Based Approach with Outcome Supervision

Eric Hanchen Jiang, Haozheng Luo, Shengyuan Pang, Xiaomin Li, Zhenting Qi, Hengli Li, Cheng-Fu Yang, Zongyu Lin, Xinfeng Li, Hao Xu, Kai-Wei Chang, Ying Nian Wu

Code

Preprint
sym

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Hengli Li, Chenxi Li, Tong Wu, Xuekai Zhu, Yuxuan Wang, Zhaoxin Yu, Eric Hanchen Jiang, Song-Chun Zhu, Zixia Jia, Ying Nian Wu, Zilong Zheng

Code

NeurIPS 2025
sym

CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs

Sijia Chen, Xiaomin Li, Mengxue Zhang, Eric Hanchen Jiang, Qingcheng Zeng, Chen-Hsiang Yu

Dataset

πŸ“– Educations

  • 2025.06 - 2030.06, University of California, Los Angeles (UCLA) (PhD)
  • 2022.06 - 2025.06, University of California, Los Angeles (UCLA) (BS)

πŸ’Ό Internship Experience

  • 2025.06 - 2025.09, Alibaba Inc.
  • 2023.01 - 2025.03, Morgan Stanley

πŸŽ– Honors and Awards

  • 2025.09 Awarded Graduate Dean’s Scholar Award (GDSA), Amount: $14,500.
  • 2025.06 Awarded Cum Laude.