Junda Wu
Scholar

Junda Wu

Google Scholar ID: _iKeQFwAAAAJ
University of California San Diego
Natural Language ProcessingRecommender SystemMultimodal LearningReinforcement Learning
Google Scholar↗
Citations & Impact
All-time
Citations
786
 
H-index
14
 
i10-index
21
 
Publications
20
 
Co-authors
5
list available
Contact
No contact links provided.
Publications
41 items
SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
2026
Cited
0
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
2026
Cited
0
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
2026
Cited
0
FERA: Uncertainty-Aware Federated Reasoning for Large Language Models
2026
Cited
0
MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization
2026
Cited
0
Skill-R1: Agent Skill Evolution via Reinforcement Learning
2026
Cited
0
Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
2026
Cited
0
A Survey on LLM-based Conversational User Simulation
2026
Cited
0
Resume (English only)
Co-authors
5 total
Julian McAuley
Julian McAuley
Professor, UC San Diego
Tong Yu
Tong Yu
Adobe Research
Lina Yao
Lina Yao
Science Lead at CSIRO Data61 & Professor at University of New South Wales, Australia
Jingbo Shang
Jingbo Shang
Associate Professor, UC San Diego
Xintong Li
Xintong Li
UC San Diego