Ming Jin
Scholar

Ming Jin

Google Scholar ID: YdxdTtkAAAAJ
Virginia Tech
AI/MLReinforcement LearningOptimizationResilience
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
3,606
 
H-index
31
 
i10-index
53
 
Publications
20
 
Co-authors
13
list available
Contact
No contact links provided.
Publications
11 items
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
2026
Cited
0
Memory-Induced Tool-Drift in LLM Agents
2026
Cited
0
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
2026
Cited
0
What Makes a Good AI Review? Concern-Level Diagnostics for AI Peer Review
2026
Cited
0
LLMs Should Express Uncertainty Explicitly
2026
Cited
0
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
2026
Cited
0
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
2026
Cited
0
IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
2026
Cited
0
Resume (English only)
Co-authors
13 total
Costas Spanos
Costas Spanos
Professor of Electrical Engineering and Computer Sciences, University of California, Berkeley
Ruoxi Jia
Ruoxi Jia
Assistant Professor, Virginia Tech
Javad Lavaei
Javad Lavaei
Associate Professor, UC Berkeley
Bilgehan Sel
Bilgehan Sel
Virginia Tech
Alexandre Bayen
Alexandre Bayen
Professor Electrical Engineering and Computer Science, UC Berkeley
Vanshaj Khattar
Vanshaj Khattar
PhD Candidate, Virginia Tech
Yi Zeng
Yi Zeng
PhD Candidate, Virginia Tech
Lillian J. Ratliff
Lillian J. Ratliff
Associate Professor, University of Washington