Zijing Ou

Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design

Memory-Driven Self-Improvement with Large Language Models

Neural Flow Samplers with Shortcut Models

Towards Training One-Step Diffusion Models Without Distillation

Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching

Neural Mutual Information Estimation with Vector Copulas

Discrete Neural Flow Samplers with Locally Equivariant Transformer

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion

Neural Mutual Information Estimation with Reference Distributions

TabUnite: Efficient Encoding Schemes for Flow and Diffusion Tabular Generative Models

Distilled Diffusion Language Models