Alborz Geramifard
Scholar

Alborz Geramifard

Google Scholar ID: 5tT42pwAAAAJ
Research Scientist Director at Meta
Reinforcement LearningConversational AIPlanningBrain and Cognitive Sciences
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
2,274
 
H-index
23
 
i10-index
43
 
Publications
20
 
Co-authors
30
list available
Contact
No contact links provided.
Publications
5 items
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
2026
Cited
0
TIP: Token Importance in On-Policy Distillation
2026
Cited
0
SODA: Semi On-Policy Black-Box Distillation for Large Language Models
2026
Cited
0
Agentic Reinforcement Learning for Real-World Code Repair
2025
Cited
0
Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs
2025
Cited
0
Resume (English only)
Co-authors
30 total
Jonathan P. How
Jonathan P. How
Ford Professor of Engineering, AA Dept., Massachusetts Institute of Technology
Nicholas Roy
Nicholas Roy
MIT
Satwik Kottur
Satwik Kottur
Research Scientist, Facebook AI
Seungwhan Moon
Seungwhan Moon
Facebook, Carnegie Mellon University
Ahmad Beirami
Ahmad Beirami
Google DeepMind
Co-author 6
Co-author 6
Michael Bowling
Michael Bowling
Amii, University of Alberta
Nazim Kemal Ure
Nazim Kemal Ure
Stanford University