2026 SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer Junsong Chen*, Yuyang Zhao*, Jincheng Yu*, Ruihang Chu, and 16 more authors In ICLR 2026 Oral Website PDF Code LongLive: Real-time Interactive Long Video Generation Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, and 8 more authors In ICLR 2026 Website PDF Code StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation Tianrui Feng, Zhi Li, Shuo Yang, Haocheng Xi, and 10 more authors In MLSys 2026 Website PDF Code 2025 Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation Xingyang Li*, Muyang Li*, Tianle Cai, Haocheng Xi, and 10 more authors In NeurIPS 2025 Website PDF Code Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation Shuo Yang*, Haocheng Xi*, Yilong Zhao, Muyang Li, and 10 more authors In NeurIPS 2025 Spotlight Website PDF Code Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models Lvmin Zhang, Shengqu Cai, Muyang Li, Gordon Wetzstein, and 1 more author NeurIPS 2025 Spotlight Website PDF Code Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity Haocheng Xi*, Shuo Yang*, Yilong Zhao, Chenfeng Xu, and 10 more authors In ICML 2025 Website PDF Code SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer Enze Xie*, Junsong Chen*, Yuyang Zhao, Jincheng Yu, and 10 more authors In ICML 2025 Website PDF Demo Code STORM: Token-Efficient Long Video Understanding for Multimodal LLMs Jindong Jiang*, Xiuyu Li*, Zhijian Liu, Muyang Li, and 12 more authors In ICCV CLVL 2025 Website PDF SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models Muyang Li*, Yujun Lin*, Zhekai Zhang*, Tianle Cai, and 6 more authors In ICLR 2025 Spotlight Website PDF Demo Code Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer Enze Xie*, Junsong Chen*, Junyu Chen, Han Cai, and 7 more authors In ICLR 2025 Oral Website PDF Demo Code Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models Junyu Chen*, Han Cai*, Junsong Chen, Enze Xie, and 5 more authors In ICLR 2025 Website PDF Code 2024 Condition-Aware Neural Network for Controlled Image Generation Han Cai, Muyang Li, Zhuoyang Zhang, Qinsheng Zhang, and 2 more authors In CVPR 2024 Website PDF Code DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models Muyang Li*, Tianle Cai*, Jiaxin Cao, Qinsheng Zhang, and 6 more authors In CVPR 2024 Highlight Website PDF Blog Code 2022 Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models Muyang Li, Ji Lin, Chenlin Meng, Stefano Ermon, and 2 more authors In T-PAMI & NeurIPS 2022 Website PDF Slides Video Code Lite Pose: Efficient Architecture Design for 2d Human Pose Estimation Yihan Wang, Muyang Li, Han Cai, Wei-Ming Chen, and 1 more author In CVPR 2022 PDF Slides Video Code 2020 GAN Compression: Efficient Architectures for Interactive Conditional GANs Muyang Li, Ji Lin, Yaoyao Ding, Zhijian Liu, and 2 more authors In T-PAMI & CVPR 2020 Website PDF Slides Video Code
