Weitong Zhang

The paper introduces Q-ALIGN DT, a novel framework that improves conditioned sequence models by enforcing alignment between the input return-to-go (RTG) signal and the output policy's expected Q-value, leading to superior policy controllability and performance.

LARK introduces a novel learnability-grounded approach for selecting reasoning trajectories, significantly improving the efficiency of reasoning distillation by prioritizing trajectories that the student model can learn from.