Fast and memory-efficient exact attention

Profluent-E1 family of Protein Encoder Models

MMseqs2: ultra fast and sensitive search and clustering suite

Plausibility checks for generated molecule poses.

Biological foundation modeling from molecular to genome scale

A fully open source biomolecular structure prediction model based on AlphaFold3

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.

A generalized computational framework for biomolecular modeling.

This is the official code for MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs

[NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Official PyTorch implementation for "Large Language Diffusion Models"

Muon is an optimizer for hidden layers in neural networks

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

Consistency Distilled Diff VAE

Foldseek enables fast and sensitive comparisons of large structure sets.

Codebase of the paper "Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling" (ICLR 2024)

AlphaFold Meets Flow Matching for Generating Protein Ensembles

[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.

DockQ is a single continuous quality measure for Protein, Nucleic Acids and Small Molecule Docking Models

RiboNucleic Acid (RNA) Language Model

Benchmarking DNA Language Models on Biologically Meaningful Tasks

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2