A framework for building custom AI Copilots 🤖 in-app AI chatbots, in-app AI Agents, & AI-powered Textareas.

computer vision and sports

Minimalist ML framework for Rust

A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques

Fast parallel LLM inference for MLX

The official PyTorch code for RoHM: Robust Human Motion Reconstruction via Diffusion.

4M: Massively Multimodal Masked Modeling

Swift Core ML Examples

High-performance In-browser LLM Inference Engine

Official PyTorch implementation of the CVPR 2024 paper: State Space Models for Event Cameras (Spotlight).

[WACV 2024] Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation

A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation

MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR2024 Oral)

Anthropic's educational courses

MedLSAM: Localize and Segment Anything Model for 3D Medical Images

SAM-Med3D: An Efficient 3D Model for Promptable Volumetric Medical Image Segmentation

Official implementation of SAM-Med2D

LLM training in simple, raw C/CUDA

Kolmogorov Arnold Networks

Dataset and Code for the paper "AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements"

API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

[CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

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

code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction