activity
20192026
most citedOne Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention

2 citations · 4 across the 6 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.LG2026

Trust the Critic More

Kaiyue Wen, Luke Bailey, Arvind Mahankali +1

Standard language model RL algorithms credit every token of a long rollout with the same advantage determined by the terminal reward. Actor-critic methods can provide finer-grained…

cs.LG2026

Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning

Arvind Mahankali, Kaiyue Wen, Tengyu Ma

Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generation is highly sequential, and long…