Jiaye Teng

Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap

Smoothing-Based Conformal Prediction for Balancing Efficiency and Interpretability

Rethinking Learning-based Symmetric Cryptanalysis: a Theoretical Perspective

Truncated Conformal Prediction: A Sparsity-Aware Framework for Classification

Efficient Conformal Prediction with Order-Preserving Predictions for Classifiers

What Makes Looped Transformers Perform Better Than Non-Recursive Ones (Provably)

A Pitfall in Conformal Prediction: When Shorter Intervals Are Not Better

Accelerating Feature Conformal Prediction via Taylor Approximation

Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift

Mastering Syntax, Unlocking Semantics: A Mathematically Provable Two-stage Learning Process in Transformers