Stars
Universal Robots ROS2 driver supporting CB3 and e-Series
Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
VisionOS App + Python Library to stream head / wrist / finger tracking data from Vision Pro to any robots.
[CoRL 2025] Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware
Open-source framework for the research and development of foundation models.
The simplest, fastest repository for training/finetuning small-sized VLMs.
A PyTorch native platform for training generative AI models
Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
Native Ubuntu installations for Apple silicon hardware
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
Protocol Buffers - Google's data interchange format
OctFusion: Octree-based Diffusion Models for 3D Shape Generation [SGP 2025]
Code for GEM3D: Generative Medial Abstractions for 3D Shape Synthesis
[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Graphormer is a general-purpose deep learning backbone for molecular modeling.
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
verl: Volcano Engine Reinforcement Learning for LLMs
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
slime is an LLM post-training framework for RL Scaling.
Deep learned, NVIDIA-accelerated 3D object pose estimation
Tutorial on amortized optimization for learning to optimize over continuous domains