Scholar
Baolin Peng
Google Scholar ID: u1CNjgwAAAAJ
Microsoft Research, Redmond
NLP
Dialog
Foundation Models
Alignment
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
7,223
H-index
40
i10-index
80
Publications
20
Co-authors
15
list available
Publications
31 items
SecureVibe: Making Vibe Coding More Secure
2026
Cited
0
Certified Long-Horizon Code Agent Evolution via Validation-Gated Skill Optimization
2026
Cited
0
ExecCritic: Learn to Test, Test to Improve for Coding Agents
2026
Cited
0
FrogNano: Training a 4B Coding Agent via Online Task Synthesis
2026
Cited
0
OpenForgeRL: Train Harness-native Agents in Any Environment
2026
Cited
0
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
2026
Cited
0
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
2026
Cited
0
Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior
2026
Cited
0
Load more
Co-authors
13 total
Jianfeng Gao
Microsoft Research, Redmond
Pengcheng He
Microsoft
kam-Fai Wong
chinese university of hong kong
Kaisheng Yao
Google
Hao Cheng
Microsoft Research / University of Washington
Xiujun Li
University of Washington / Apple
Wenge Rong
Beihang University
Yangyang Shi
Meta
