Masaaki Imaizumi

SONA: Learning Conditional, Unconditional, and Matching-Aware Discriminator

Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data

Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry

Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning

Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs

Distillation of Discrete Diffusion through Dimensional Correlations