🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

Memory infrastructure for LLMs and AI agents

Humanoid Agents: Platform for Simulating Human-like Generative Agents

SurgLaVi: Large-Scale Hierarchical Datasets for Surgical Vision–Language Representation Learning

[ICCV 2025] MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance

The best ChatGPT that $100 can buy.

Open-H-Embodiment is a community‑driven dataset initiative building the open, shared foundation needed to train and evaluate a generalist Vision‑Language‑Action (VLA) model for healthcare robotics

repo collection for NVIDIA Audio2Face-3D models and tools

[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

Sharing scripts and functions for OPUS-PALA article, and LOTUS Software. All functions are usable with agreement from their owner.

This repo powers my experiment where ChatGPT manages a real-money micro-cap stock portfolio.

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Large-scale Self-supervised Pre-training for Endoscopy

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Open-source implementation of AlphaEvolve

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

[CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

For IROS 2024 paper (Diego, Sabina, Michal Naskret, Przemek)

[ICLR 2025] Learning General-purpose Biomedical Volume Representations using Randomized Synthesis

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Official Repo For "Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos"

Multi-modal agentic framework for surgical procedures

MONAI Multi-modal: Central hub for medical vision-language and language models. Repository of repositories for community contributions to medical AI agents.

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

A Conversational Speech Generation Model