PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

Muon is an optimizer for hidden layers in neural networks

A tale of works on the complexity of first-order bilevel optimization.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

Official implementation for Mobi-π.

Code repository for the Habitat Synthetic Scenes Dataset (HSSD) paper.

The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

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

RoboTwin 2.0 Offical Repo

[RSS25] Official implementation of DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Python efficient farthest point sampling (FPS) library. Compatible with numpy.

[ICLR25] BID-Robot

Theia: Distilling Diverse Vision Foundation Models for Robot Learning

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

[CVPR 2024 Oral] Official repository for RALF: Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation

Official repository for "PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout" (CVPR 2023).

[ECCV2022] Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

Realize inverse kinematics in mujoco through mocap control

[RSS 2024] 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

DUSt3R: Geometric 3D Vision Made Easy