Fun repo, modular inference for long-context 3d mapping inference.

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Official implementation of VGGT-Long

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

DepthNav is a research framework for developing and evaluating autonomous navigation policies, particularly for aerial robots in complex 3D environments.

Published on Nature Machine Intelligence! The first real robot(quadrotor) based on differentiable physics training.

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

The Kalibr visual-inertial calibration toolbox

[IROS 2025] Source code for "RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration"

Assignments for CMU 16-831 Introduction to Robot Learning.

Configs and boilerplates for Label Studio's Machine Learning backend

Gemma 3n Hackathon sprint

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Notebooks illustrating usage of Transformers library by HuggingFace. Forking it as a playground!!!

[TPAMI & ECCV 2022] Contrast-Phys & Contrast-Phys+ for facial video-based remote physiological signal measurement

To overcome fundamental biases in camera-based remote plethysmography, we propose an adversarial learning-based fair fusion method, using a novel RGB-Radar hardware setup.

PyTorch code and models for the DINOv2 self-supervised learning method.

seizure type classification using TUH dataset

ANT and ANT-FS Python Library

Automatically sync leetcode solutions to github account

"stealth"