Fast and memory-efficient classical machine learning operators

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

OneDiff: An out-of-the-box acceleration library for diffusion models.

PyTorch code and models for V-JEPA self-supervised learning from video.

Fast Diffusion Models with Transformers

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Modeling, training, eval, and inference code for OLMo

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Building a quick conversation-based search demo with Lepton AI.

[ICCV 2023] StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Character Animation (AnimateAnyone, Face Reenactment)

[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

An open-source framework for training large multimodal models.

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

A simple, performant and scalable Jax LLM!

High-speed Large Language Model Serving for Local Deployment

[T-PAMI 2025] PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm

QLoRA: Efficient Finetuning of Quantized LLMs

[ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

Code for paper: FUTR3D: a unified sensor fusion framework for 3d detection

Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

[ICLR 2023] DiffMimic: Efficient Motion Mimicking with Differentiable Physics https://arxiv.org/abs/2304.03274