Huangjie Zheng

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs

Score Distillation of Flow Matching Models

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

Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting

Normalizing Flows are Capable Generative Models

TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics

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

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

What If We Recaption Billions of Web Images with LLaMA-3?

What If We Recaption Billions of Web Images with LLaMA-3?