Atsushi Nitanda

Alternating Diffusion for Proximal Sampling with Zeroth Order Queries

Smooth Calibration Error: Uniform Convergence and Functional Gradient Analysis

Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning

How Does Preconditioning Guide Feature Learning in Deep Neural Networks?

Deterministic Transport-Based Sampling via Wasserstein Gradient Flows

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training

Statistical Analysis of the Sinkhorn Iterations for Two-Sample Schr\"{o}dinger Bridge Estimation

Direct Distributional Optimization for Provable Alignment of Diffusion Models

Provable In-Context Vector Arithmetic via Retrieving Task Concepts

Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble

Memorisable Prompting: Preventing LLMs Forgetting False Positive Alarm