Publications

Ruyi Xu, Guangxuan Xiao, Haofeng Huang, Junxian Guo, Song Han (2025). XAttention: Block Sparse Attention with Antidiagonal Scoring. ICML2025.

PDF Cite Code Slides

Haocheng Xi, Shuo Yang, Yilong Zhao, Chenfeng Xu, Muyang Li, Xiuyu Li, Yujun Lin, Han Cai, Jintao Zhang, Dacheng Li, Jianfei Chen, Ion Stoica, Kurt Keutzer, Song Han (2025). Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity. ICML2025.

PDF Cite Code Project

Enze Xie, Junsong Chen, Yuyang Zhao, Jincheng Yu, Ligeng Zhu, Yujun Lin, Zhekai Zhang, Muyang Li, Junyu Chen, Han Cai, Bingchen Liu, Daquan Zhou, Song Han (2025). SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer. ICML2025.

PDF Cite Code Project

Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, Song Han (2024). SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models. ICLR2025.

PDF Cite Code Project Video Demo Blog

Haocheng Xi, Han Cai, Ligeng Zhu, Yao (Jason) Lu, Kurt Keutzer, Jianfei Chen, Song Han (2024). COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training. ICLR2025.

PDF Cite Code Project Demo

Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao (Jason) Lu, Song Han (2024). SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer. ICLR2025.

PDF Cite Code Project MIT Project Demo

Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, Song Han (2024). DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads. ICLR2025.

PDF Cite Code Project

Junyu Chen, Han Cai, Junsong Chen, Enze Xie, Shang Yang, Haotian Tang, Muyang Li, Yao (Jason) Lu, Song Han (2024). Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models. ICLR2025.

PDF Cite Code Project

Xuanyao Chen, Zhijian Liu, Haotian Tang, Li Yi, Hang Zhao, Song Han (2023). SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer. CVPR.

PDF Cite Code Project Poster

Zhijian Liu, Xinyu Yang, Haotian Tang, Shang Yang, Song Han (2023). FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer. CVPR.

PDF Cite Code Project Poster

Zhijian Liu, Haotian Tang, Alexander Amini, Xinyu Yang, Huizi Mao, Daniela L. Rus, Song Han (2022). BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation. ICRA2023.

PDF Cite Code Project Poster Video