Han Cai

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

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

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

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

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

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

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training

Accelerate High-Quality Diffusion Models with Inner Loop Feedback