Aviral Kumar
Scholar

Aviral Kumar

Google Scholar ID: zBUwaGkAAAAJ
Carnegie Mellon University
AIReinforcement Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
25,605
 
H-index
50
 
i10-index
70
 
Publications
20
 
Co-authors
8
list available
Contact
No contact links provided.
Publications
37 items
Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching
2026
Cited
0
$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning
2026
Cited
0
Adaptation of Generalist Robot Policies with Minimal Data
2026
Cited
0
MIRROR: Learning from the Other View for Multi-Modal Reasoning
2026
Cited
0
Addressing Over-Refusal in LLMs with Competing Rewards
2026
Cited
0
ExpRL: Exploratory RL for LLM Mid-Training
2026
Cited
0
AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents
2026
Cited
0
Recursive Agent Optimization
2026
Cited
0
Resume (English only)
Co-authors
8 total
Sergey Levine
Sergey Levine
UC Berkeley, Physical Intelligence
George Tucker
George Tucker
Google DeepMind
Chelsea Finn
Chelsea Finn
Stanford University, Physical Intelligence
Rishabh Agarwal
Rishabh Agarwal
Meta, ex DeepMind, Google Brain
Anikait Singh
Anikait Singh
Stanford University
Tianhe Yu
Tianhe Yu
Google DeepMind
Aurick Zhou
Aurick Zhou
Google DeepMind
Kevin Swersky
Kevin Swersky
Google Brain