Junkai Zhang 张峻恺

Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training

Junkai Zhang*, Zihao Wang*, Lin Gui*, Swarnashree Mysore Sathyendra, Jaehwan Jeong, Victor Veitch, Wei Wang, Yunzhong He, Bing Liu, Lifeng Jin

[Paper] [Code] [Dataset]

In Submission, available on arXiv

DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails

Yihe Deng*, Yu Yang*, Junkai Zhang*, Wei Wang, Bo Li

[Paper] [Code] [Model]

In Submission, available on arXiv

MatSciBench: Benchmarking the Reasoning Ability of LLM in Material Science

Junkai Zhang*, Jingru Gan*, Zian Jia, Changquan Gu, Jianpeng Chen, Xiaoxuan Wang, Yanqiao Zhu, Mingyu Derek Ma, Dawei Zhou, Ling Li, Wei Wang

[Paper] [Code] [Dataset]

In Submission, available on arXiv

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

Protein Large Language Models: A Comprehensive Survey

Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang

[Paper]

EMNLP 2025 Findings

MetamatBench: Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery

Jianpeng Chen, Wangzhi Zhan, Haohui Wang, Zian Jia, Jingru Gan, Junkai Zhang, Jingyuan Qi, Tingwei Chen, Lifu Huang, Muhao Chen, Ling Li, Wei Wang, Dawei Zhou

[Paper] [Code]

KDD 2025 Datasets and Benchmarks Track

Neural network-assisted personalized handwriting analysis for Parkinson's disease diagnostics

Guorui Chen, Trinny Tat, Yihao Zhou, Zhaoqi Duan, Junkai Zhang, Kamryn Scott, Xun Zhao, Zeyang Liu, Wei Wang, Song Li, Katy A. Cross, Jun Chen

[Paper]

Nature Chemical Engineering

Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems

Zijie Huang*, Jeehyun Hwang*, Junkai Zhang*, Jinwoo Baik, Weitong Zhang, Quanquan Gu, Dominik Wodarz, Yizhou Sun, Wei Wang

[Paper]

ACM Web Conference (WWW) 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

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs

Junkai Zhang, Weitong Zhang, Quanquan Gu

[Paper]

International Conference on Machine Learning (ICML) 2023

Fast Sampling via De-randomization for Discrete Diffusion Models

Zixiang Chen, Huizhuo Yuan, Yongqian Li, Yiwen Kou, Junkai Zhang, Quanquan Gu

[Paper] [Code]

Advances in Neural Information Processing Systems (NeurIPS) 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

About

Education

Professional Experience

Publications & Manuscripts

Selected Works

AI for Science

Reinforcement Learning

Generative Models

Optimization Methods

Teaching

Academic Services

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

Oct. 2025 -- Present Google, Playa Vista, CA, U.S. Student Researcher

Jun. 2025 -- Sep. 2025 Scale AI, San Francisco, CA, U.S. Post-training Research Intern