Arian Hosseini

Shape of Thought: When Distribution Can Matter More than Correctness in Reasoning Tasks

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

Not All LLM Reasoners Are Created Equal

Generative Verifiers: Reward Modeling as Next-Token Prediction