Scholar
Alborz Geramifard
Google Scholar ID: 5tT42pwAAAAJ
Research Scientist Director at Meta
Reinforcement Learning
Conversational AI
Planning
Brain and Cognitive Sciences
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,274
H-index
23
i10-index
43
Publications
20
Co-authors
30
list available
Publications
12 items
Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts
2026
Cited
0
Hierarchical Reinforcement Learning with Stable Temporal Abstraction for Language Model Agents
2026
Cited
0
AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning
2026
Cited
0
SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning
2026
Cited
0
Smaller Models, Better Rejects: Preference Distillation Scaling
2026
Cited
0
TREK: Distill to Explore, Reinforce to Refine
2026
Cited
0
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
2026
Cited
0
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
2026
Cited
0
Load more
Co-authors
15 total
Jonathan P. How
Ford Professor of Engineering, AA Dept., Massachusetts Institute of Technology
Nicholas Roy
MIT
Satwik Kottur
Research Scientist, Facebook AI
Seungwhan Moon
Facebook, Carnegie Mellon University
Ahmad Beirami
Google DeepMind
Michael Bowling
Amii, University of Alberta
Nazim Kemal Ure
Stanford University
Richard S. Sutton
Keen, Amii, and University of Alberta
