Jiajun Chai
Scholar

Jiajun Chai

Google Scholar ID: yDdfap0AAAAJ
Meituan Inc.
Reinforcement LearningLLMsAgentic Learning
Google Scholar↗
Citations & Impact
All-time
Citations
209
 
H-index
6
 
i10-index
5
 
Publications
20
 
Co-authors
5
list available
Contact
No contact links provided.
Publications
17 items
CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling
2026
Cited
0
SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
2026
Cited
0
Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
2026
Cited
0
Your Group-Relative Advantage Is Biased
2026
Cited
6
AWPO: Enhancing Tool-Use of Large Language Models through Explicit Integration of Reasoning Rewards
2025
Cited
0
ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIs
2025
Cited
0
LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services
2025
Cited
0
Training Multi-Image Vision Agents via End2End Reinforcement Learning
2025
Cited
0
Resume (English only)
Co-authors
5 total
Yuanheng Zhu
Yuanheng Zhu
Institute of Automation, Chinese Academy of Sciences
Dongbin Zhao
Dongbin Zhao
Institute of Automation, Chinese Academy of Sciences
Yuqian Fu
Yuqian Fu
Institute of Automation，Chinese Academy of Sciences
Guojun Yin
Guojun Yin
Meituan, University of Science and Technology of China
Mingrui Yu (于铭瑞)
Mingrui Yu (于铭瑞)
PhD student, Department of Automation, Tsinghua University