Arian Hosseini
Scholar

Arian Hosseini

Google Scholar ID: MV7LPnEAAAAJ
Research Scientist, Google DeepMind, Mila
ReasoningAlignmentPlanningGeneralization
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,139
 
H-index
14
 
i10-index
15
 
Publications
19
 
Co-authors
22
list available
Contact
TwitterOpen ↗GitHubOpen ↗
Publications
6 items
Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
2025
Cited
0
Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
2025
Cited
0
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
2025
Cited
0
When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
2025
Cited
0
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
arXiv.org · 2024
Cited
2
Generative Verifiers: Reward Modeling as Next-Token Prediction
arXiv.org · 2024
Cited
55
Resume (English only)
Co-authors
22 total
Alessandro Sordoni
Alessandro Sordoni
Microsoft Research
Rishabh Agarwal
Rishabh Agarwal
Meta, ex DeepMind, Google Brain
Aaron Courville
Aaron Courville
Professor, DIRO, Université de Montréal, Mila, Cifar CAI chair
Dzmitry Bahdanau
Dzmitry Bahdanau
ServiceNow Research
Hritik Bansal
Hritik Bansal
University of California Los Angeles | Indian Institute of Technology Delhi
Mehran Kazemi
Mehran Kazemi
Staff Research Scientist, Google DeepMind
Xingdi Yuan
Xingdi Yuan
Microsoft Research, Montreal
Shengyi Huang
Shengyi Huang
Allen Institute for Artificial Intelligence