Weihua Du
Scholar

Weihua Du

Google Scholar ID: 6CqQ4L8AAAAJ
LTI, Carnegie Mellon University
language modelsreinforcement learningembodied AI
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
466
 
H-index
5
 
i10-index
3
 
Publications
11
 
Co-authors
13
list available
Contact
Emailweihuada@cs.cmu.eduCVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
12 items
Reinforcing Human Behavior Simulation via Verbal Feedback
2026
Cited
0
Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
2026
Cited
0
The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
2026
Cited
0
AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation
2026
Cited
0
Mind the Sim2Real Gap in User Simulation for Agentic Tasks
2026
Cited
0
GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
2026
Cited
0
Training Proactive and Personalized LLM Agents
2025
Cited
0
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
2025
Cited
0
Resume (English only)
Co-authors
13 total
Hongxin Zhang
Hongxin Zhang
University of Massachusetts, Amherst
Chuang Gan
Chuang Gan
UMass Amherst | MIT-IBM Watson AI Lab
Yilun Du
Yilun Du
Harvard University
Joshua B. Tenenbaum
Joshua B. Tenenbaum
MIT
Qinhong Zhou
Qinhong Zhou
University of Massachusetts Amherst
Tianmin Shu
Tianmin Shu
Assistant Professor, JHU
Zehui Chen
Zehui Chen
USTC
Wenwei Zhang
Wenwei Zhang
Shanghai AI Laboratory