Mohammad Ghavamzadeh
Scholar

Mohammad Ghavamzadeh

Google Scholar ID: Bo-wyrkAAAAJ
Amazon AGI
Reinforcement LearningOnline LearningMachine LearningControlAI
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
13,324
 
H-index
48
 
i10-index
121
 
Publications
20
 
Co-authors
42
list available
Contact
GitHubOpen ↗
Publications
9 items
Displacement-Resistant Extensions of DPO with Nonconvex $f$-Divergences
2026
Cited
0
DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning
2026
Cited
0
Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains
2026
Cited
1
Directional-Clamp PPO
2025
Cited
0
Does Thinking More always Help? Understanding Test-Time Scaling in Reasoning Models
2025
Cited
0
Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models
2025
Cited
0
C-3DPO: Constrained Controlled Classification for Direct Preference Optimization
2025
Cited
0
Preference Optimization via Contrastive Divergence: Your Reward Model is Secretly an NLL Estimator
2025
Cited
0
Resume (English only)
Research Experience
  • Senior Principal Scientist, Amazon AGI (2023–present)
  • Senior Staff Research Scientist, Google Research (2020–2023)
  • Senior Research Scientist, Facebook AI Research (2018–2020)
  • Staff Research Scientist, DeepMind (2017–2018)
  • Senior Analytics Researcher, Adobe Research (2013–2017)
  • Chargé de recherche, INRIA Lille – Team SequeL (2008–2013)
Co-authors
42 total
Yinlam Chow
Yinlam Chow
Research Scientist, Google Research
Alessandro Lazaric
Alessandro Lazaric
Research Scientist, Facebook Artificial Intelligence Research
Shie Mannor
Shie Mannor
Professor of Electrical Engineering @ Technion & Researcher @ Nvidia
Branislav Kveton
Branislav Kveton
Adobe Research
Rémi Munos
Rémi Munos
FAIR, Meta
Craig Boutilier
Craig Boutilier
Principal Scientist, Google
Sridhar Mahadevan
Sridhar Mahadevan
Director, Adobe Research & Professor, University of Massachusetts, Amherst
Csaba Szepesvari
Csaba Szepesvari
DeepMind & University of Alberta