Haocheng Xi

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

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

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

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

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation

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

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference

Oscillation-Reduced MXFP4 Training for Vision Transformers

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

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

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