Shaokun Zhang College of Information Science and Technology Pennsylvania State University E-mail: shaokun.zhang@psu.edu Github   Twitter   Google Scholor

LLM-powered Agents  AutoML

• Autogen: LLM agents
  Role: one of the creators. (25.3 k stars, mentioned by Microsoft CEO Satya Nadella)
  
• FLAML: AutoML and hyperparameter tuning
  Role: main maintainer. (3.3k stars, 1 millon downloads)
  

• Training Language Model Agents without Modifying Language Models
  Shaokun Zhang*, Jieyu Zhang*, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, Qingyun Wu
  Forty-first International Conference on Machine Learning (ICML)
  Vienna, Austria, July, 2024

• Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
  Xiaobo Xia, Jiale Liu, Shaokun Zhang, Qingyun Wu, Hongxin Wei, Tongliang Liu
  Forty-first International Conference on Machine Learning (ICML)
  Vienna, Austria, July, 2024

• IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
  Shaokun Zhang*, Xiaobo Xia*, Zhaoqing Wang, Lin-Hao Chen, Jiale Liu, Qingyun Wu, Tongliang Liu
  Eleventh International Conference on Learning Representations (ICLR)
  Vienna, Austria, May, 2024

• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
  Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang
  ICLR 2024 Workshop on LLMAgents (Best Paper Award)
  Vienna, Austria, May, 2024

• An Empirical Study on Challenging Math Problem Solving with GPT-4
  Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, Chi Wang
  ICLR 2024 Workshop on LLMAgents
  Vienna, Austria, May, 2024

• Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
  Shaokun Zhang, Feiran Jia, Chi Wang, Qingyun Wu
  Eleventh International Conference on Learning Representations (ICLR) (Oral Presentation, 91/4955=2.39%)
  Kigali, Rwanda, May, 2023

• Efficient Neural Architecture Search via Dynamic Distribution Pruning
  Xiawu Zheng, Chenyi Yang, Shaokun Zhang, Yan Wang, Baochang Zhang, Yongjian Wu, Yunsheng Wu, Ling Shao, Rongrong Ji
  International Journal of Computer Vision 131.5 (2023): 1234-1249 (IJCV)
  

• StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
  Yiran Wu, Tianwei Yue, Shaokun Zhang, Chi Wang, Qingyun Wu
  Preprint 2024
  

• HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts
  Shaokun Zhang, Yiran Wu, Zhonghua Zheng, Qingyun Wu, Chi Wang
  Preprint 2023
  

• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
  Shaokun Zhang, Xiawu Zheng, Chenyi Yang, Yuchao Li, Yan Wang, Fei Chao, Mengdi Wang, Shen Li, Jun Yang, Rongrong Ji
  Preprint 2021
  

(*equal contribution)

• Reinforcement Learning Open-Source Fest Award, Microsoft Research at NYC, 2022.
• The First Prize Scholarship, Xidian University, 2019.
• Chinese National Scholorship, Ministry of Education of China, 2018.
• Excellent Student Title at Xidian Univ, Xidian University, 2018.

• DS 440: Data Sciences Capstone Course
  Instructor/Teaching Assistant, Penn State, Spring 2023 & Fall 2023.
  

• Conference Reviewer:
• ICLR'24, NeurIPS'23, ACL'23, ICML'24
• UAI'23, AutoML'23, KDD'24
• AJCAI'23, ICIC'23
• Journal Reviewer:
• TCSVT
• Information Fusion