代码库
Code for "DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training"
Python
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++
Python
auto-regressive-diffusion-modelautoregressive-modelsconsistency-modelsdiffusiondiffusion-modelsdistillationfew-step-generationgenerative-aitext-to-videotext-to-video-generationvideo-diffusion-modelvideo-generationwan-videowan2wan21world-modelworld-models
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
Cuda
ai-infraattentioninference-accelerationllmmlsysquantizationsageattentionsparse-attentionvideo-generationvision-transformervit
Official code of Motus: A Unified Latent Action World Model
Python
diffusion-modelrobotic-manipulationroboticsunidiffuservideo-generationvision-language-action-modelworld-model
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Python
An elegant PyTorch deep reinforcement learning library.
Python
a2cataribcqcqlddpgdouble-dqndqndrlimitation-learningmujoconpgpolicy-gradientppopytorchrlsactd3transferlabtrpo
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
Cuda
attentioncudaefficient-attentioninference-accelerationllmllm-inframlsysquantizationtritonvideo-generatevideo-generationvit
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage
Python
cogvideoxdiffusiondiffusion-modelsdiffusion-transformerditextrapolationgenerative-modelhunyuan-videolong-video-generationposition-embeddingropevideo-generation