Inference code for Llama models

The official Python library for the OpenAI API

TradingAgents: Multi-Agents LLM Financial Trading Framework

Python sample codes and textbook for robotics algorithms.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

A TTS model capable of generating ultra-realistic dialogue in one pass.

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Pocket Flow: Codebase to Tutorial

Fast Segment Anything

DUSt3R: Geometric 3D Vision Made Easy

Point cloud diffusion for 3D model synthesis

Unified framework for robot learning built on NVIDIA Isaac Sim

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

Visual localization made easy with hloc

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

Curated list of awesome Cursor Rules .mdc files

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…

[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you alre…

PyTorch pre-trained model for real-time interest point detection, description, and sparse tracking (https://arxiv.org/abs/1712.07629)

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

ViPE: Video Pose Engine for Geometric 3D Perception

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields. https://arxiv.org/abs/2210.13641 + Sigma-Fusion: Probabilistic Volumetric Fusion for Dense Monocular SLAM https://arxiv.org/ab…