Ruida Zhou

Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback

Alignment from Ranking and Rating Information

On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

On the Training Convergence of Transformers for In-Context Classification

Correlational Lagrangian Schrodinger Bridge: Learning Dynamics with Population-Level Regularization

On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures

Transformers Learn Variable-order Markov Chains in-Context