Me
Junkai Zhang (张峻恺)
CS PHD Student @ UCLA

About

I'm now a third-year Ph.D. student in the Computer Science Department at UCLA. I am fortunate to be advised by Professor Wei Wang. I am broadly interested in machine learning. I received my B.S. degree in Mathematics from Tsinghua University in 2022, with a minor in Philosophy

Education


Ph.D.           Sep. 2022 - Present
                     University of California, Los Angeles (UCLA), Los Angeles, CA, U.S.
                     Ph.D. student in Computer Science
B.S.              Aug. 2018 - Jun. 2022
                     Tsinghua University (THU), Beijing, China.
                     B.S. in Mathematics, Minor in Philosophy

Publications & Manuscripts

DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Yihe Deng*, Yu Yang*, Junkai Zhang*, Wei Wang, Bo Li
[Paper] [Model]
MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design
Jingyuan Qi, Zian Jia, Minqian Liu, Wangzhi Zhan, Junkai Zhang, Xiaofei Wen, Jingru Gan, Jianpeng Chen, Qin Liu, Mingyu Derek Ma, Bangzheng Li, Haohui Wang, Adithya Kulkarni, Muhao Chen, Dawei Zhou, Ling Li, Wei Wang, Lifu Huang
[Paper] [Demo]
NAACL 2025 - Demo Track
Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
Zixiang Chen, Huizhuo Yuan, Yongqian Li, Yiwen Kou, Junkai Zhang, Quanquan Gu
[Paper]
Advances in Neural Information Processing Systems (NeurIPS 2024)
Uncertainty-Aware Reward-Free Exploration with General Function Approximation
Junkai Zhang*, Weitong Zhang*, Dongruo Zhou, Quanquan Gu
[Paper] [Code]
International Conference on Machine Learning (ICML 2024)
Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems
Zijie Huang*, Jeehyun Hwang*, Junkai Zhang*, Xiuyuan Wang, Jinwoo Baik, Weitong Zhang, Dominik Wodarz, Yizhou Sun, Quanquan Gu, Wei Wang
[Paper]
The Web Conference (WWW 2024)
Why Does Sharpness-Aware Minimization Generalize Better Than SGD?
Zixiang Chen*, Junkai Zhang*, Yiwen Kou, Xiangning Chen, Cho-Jui Hsieh, Quanquan Gu
[Paper]
Advances in Neural Information Processing Systems (NeurIPS 2023)
Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
Junkai Zhang, Weitong Zhang, Quanquan Gu
[Paper]
International Conference on Machine Learning (ICML 2023)

Selected Honors & Awards

  • ICML 2024 Travel Award, 2024
  • NeurlPS 2023 Scholar Award, 2023

Teaching

  • CS 31/32: Introduction to Computer Science - Fall 2023 - Winter 2024
         Teaching Assistant (TA)

    • Academic Services

    Conference Reviewer: ICLR, ICML, AAAI, AISTATS, NAACL
    Volunteer: NeurIPS 2024
    Top