Enze Xie

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

LongLive: Real-time Interactive Long Video Generation

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

Fast-dLLM v2: Efficient Block-Diffusion LLM

ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World Simulation

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers

SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation