Yingcong Li

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning

Theoretical Insights into In-context Learning with Unlabeled Data

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning

Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond