Weihua Du

PhD student, LTI, Carnegie Mellon University

Joined

September 2022

Names

Weihua Du (Preferred)

Emails

****@mails.tsinghua.edu.cn (Confirmed)

****@andrew.cmu.edu (Confirmed)

****@cs.cmu.edu (Confirmed)

Personal Links

Career & Education History

PhD student

LTI, Carnegie Mellon University (cmu.edu)

2024 – Present

Undergrad student

IIIS, Tsinghua University (mails.tsinghua.edu.cn)

2020 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Sean Welleck

2024 – Present

PhD Advisor

Yiming Yang

2024 – Present

Coauthor

Hongxin Zhang

2023 – 2024

Advisor

Chuang Gan

2023 – 2024

Advisor

Yi Wu

2022 – 2023

Coauthor

Wei Fu

2022 – 2023

Expertise

reinforcement learning

Present

generative agent

Present

large language models

Present

Publications

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
Miao Lu, Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
Weihua Du, Hailei Gong, Zhan Ling, Kang Liu, Lingfeng Shen, Xuesong Yao, Yufei Xu, Dingyuan Shi, Yiming Yang, Jiecao Chen
- ICLR 2026 Poster
- Readers: Everyone
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
Feijiang Han, Xiaodong Yu, Jianheng Tang, Delip Rao, Weihua Du, Lyle Ungar
- ICLR 2026 Poster
- Readers: Everyone
Optimizing Temperature for Language Models with Multi-Sample Inference
Weihua Du, Yiming Yang, Sean Welleck
- ICML 2025 poster
- Readers: Everyone
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step
Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao
- OpenReview Archive Direct Upload
- Readers: Everyone
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Weihua Du, Qiushi Lyu, Jiaming Shan, Zhenting Qi, Hongxin Zhang, Sunli Chen, Andi Peng, Tianmin Shu, Kwonjoon Lee, Behzad Dariush, Chuang Gan
- NeurIPS 2024 Track Datasets and Benchmarks Poster
- Readers: Everyone
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step
Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao
- OpenReview Archive Direct Upload
- Readers: Everyone
Building Cooperative Embodied Agents Modularly with Large Language Models
Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua Tenenbaum, Tianmin Shu, Chuang Gan
- FMDM@NeurIPS2023
- Readers: Everyone
Building Cooperative Embodied Agents Modularly with Large Language Models
Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B. Tenenbaum, Tianmin Shu, Chuang Gan
- ICLR 2024 poster
- Readers: Everyone
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
Qinhong Zhou, Sunli Chen, Yisong Wang, Haozhe Xu, Weihua Du, Hongxin Zhang, Yilun Du, Joshua B. Tenenbaum, Chuang Gan
- ICLR 2024 poster
- Readers: Everyone

View all 12 publications

Co-Authors

View all 46 co-authors