Zesheng Shi
Scholar

Zesheng Shi

Google Scholar ID: iUDarq8AAAAJ
Harbin Institute of Technology
nlp
Google Scholar↗
Citations & Impact
All-time
Citations
18
 
H-index
3
 
i10-index
0
 
Publications
7
 
Co-authors
3
list available
Contact
No contact links provided.
Publications
10 items
Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry
2026
Cited
0
Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
2026
Cited
0
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
2026
Cited
0
Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
2026
Cited
0
E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
2026
Cited
0
MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision
2025
Cited
0
Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
2025
Cited
0
Safety Alignment via Constrained Knowledge Unlearning
2025
Cited
1
Resume (English only)
Co-authors
3 total
Yucheng Zhou
Yucheng Zhou
University of Macau | Fudan
GUODONG DU
GUODONG DU
National University of Singapore
Weiyang Guo
Weiyang Guo
Harbin Institute of Technology, Shenzhen