Ruixiang ZHANG

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

What makes the preferred thinking direction for LLM in Multi-choice Questions?

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

Normalizing Flows are Capable Generative Models

Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows

Discrete Neural Flow Samplers with Locally Equivariant Transformer

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion

dMel: Speech Tokenization Made Simple

Distilled Diffusion Language Models