Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena

[ICCV 2025 Oral] Official implementation of Learning Streaming Video Representation via Multitask Training.

NeuralMD for Protein-ligand Binding Simulation, Nature Communicaitons 2025

Get chemical SMILES strings (structures) based on the CAS numbers or the names of the chemicals.

A high-throughput and memory-efficient inference and serving engine for LLMs

A fully open source biomolecular structure prediction model based on AlphaFold3

ProTrek: illuminating the Protein Universe through Trimodal Protein Language Model

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Electron Density-enhanced Molecular Geometry Learning (IJCAI 2025)

Diffusion Recommender Model

[ICLR 2024] Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models

Combinatorial antibiotic generation

MiMo-VL

[CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.

[NeurIPS 2025 D&B🔥] OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

Open-source unified multimodal model

EDBench: Large-Scale Electron Density Data for Molecular Modeling (NeurIPS 2025)

FAIR Chemistry's library of machine learning methods for chemistry

A PyTorch Library for Accelerating 3D Deep Learning Research

Open3D: A Modern Library for 3D Data Processing

Kolmogorov Arnold Networks

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

OpenMMLab's next-generation platform for general 3D object detection.

[CVPR 2025] Official codes for the paper 'Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models'

[ECCV 2024] ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

OpenPoints: a library for easily reproducing point-based methods for point cloud understanding. The engine for [PointNeXt](https://arxiv.org/abs/2206.04670)

A Python library for 3d image data augmentation. Useful for machine learning.

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

This is a complete package of recent deep learning methods for 3D point clouds in pytorch (with pretrained models).