Stars
A differentiable bridge between phase space and Fock space
Coherence decay and dynamical decoupling benchmarks on IBM Heron processors using GHZ, W, and cluster states on baseline-access IBM Quantum hardware.
PDK for GlobalFoundries' 180nm MCU bulk process technology (GF180MCU).
A minimal implementation of DeepMind's Genie world model
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
🎥 Make videos programmatically with React
GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
A collection of tabletop tasks in Mujoco
[ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
NVIDIA Isaac Sim™ is an open-source application on NVIDIA Omniverse for developing, simulating, and testing AI-driven robots in realistic virtual environments.
Scalable toolkit for efficient model reinforcement
A fast and simple implementation of learning algorithms for robotics.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Topology optimization for linear elastic minimum compliance with volume constraints on cartesian grids in 3D using PETSc.
Generator of runtime monitors for flight and robotics applications.
A stream-based runtime-verification framework for generating hard real-time C code.
Official implementation of Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration
Official Implementation of the ICLR 2024 spotlight paper: Universal Humanoid Motion Representations for Physics-Based Control
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
Official implementation of "OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning"
Implementation of Latent Diffusion Planning (Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn)