Stars
[ICML'26] LEMUR reduces multi-vector retrieval for late interaction models such as ColBERT into regular single-vector retrieval.
TopoBench is a Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning
Information and organization of the STIMA Machine Learning Reading Group
An extremely fast Python package and project manager, written in Rust.
An extremely fast Python linter and code formatter, written in Rust.
A package to train machine learning models on geospatial data, mainly for weather and climate. Used to run ArchesWeather and ArchesWeatherGen
A 15TB Collection of Physics Simulation Datasets
Large-Scale Multimodal Dataset of Astronomical Data
A two-dimensional triangular mesh generator with pre- and post-processing utilities written in pure MATLAB (no toolboxes required) designed specifically to build models that solve shallow-water equ…
[NeurIPS'24] Approximate Nearest Neighbor search using reduced-rank regression, with extremely fast queries, tiny memory usage, and rapid indexing on modern vector embeddings.
An open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators.
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.
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.
Figure sizes, font sizes, fonts, and more configurations at minimal overhead. Fix your journal papers, conference proceedings, and other scientific publications.
[MICCAI 2023] MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.
Code for EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch
Research Software for Neural Weather Prediction for Limited Area Modeling
Initial public release of code, data, and model weights for FourCastNet
Run AI-based weather forecasting models with ECMWF data
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.
Demo of Multi-scale Deep Convolutional Neural Networks
A portfolio management algorithm for the 21st century.
Graph-based weather forecasting models. Originally, PyTorch implementation of Ryan Keisler's 2022 "Forecasting Global Weather with Graph Neural Networks" paper (https://arxiv.org/abs/2202.07575)