A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Robust Speech Recognition via Large-Scale Weak Supervision

[NeurIPS 2023] Official code release for the paper: "Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?"

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

Python inverse kinematics based on MuJoCo

Stable Diffusion web UI

The official PytTorch implementation of "Mix-Spectrum for Generalization in Visual Reinforcement Learning"

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

Use TensorRT to accelerate the Depth-Anything-V2 model for monocular depth estimation. Support batch inference.

【编程随想】收藏的电子书清单（多个学科，含下载链接）

[RSS 2024] Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation

High-performance and seamless sharing and modification of Python objects between processes, without the periodic overhead of serialization and deserialization. Provides fast inter-process communica…

Simple wrapper around the Shared Array library

Unified framework for robot learning built on NVIDIA Isaac Sim

Distilling Diffusion Policy into consistency models

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

Code Notes (in Chinese) for 3D Gaussian Splatting

NF-Layers for constructing neural functionals.

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"

⚡ Flashbax: Accelerated Replay Buffers in JAX

[ICLR2024] Official repo for paper "PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code"

Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusion robotics papers.

Really Fast End-to-End Jax RL Implementations

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

Code for subgoal synthesis via image editing