A benchmark for comprehensive evaluation on protein structure tokenization methods

Public Release of ProGen3 family of Models

Profluent-E1 family of Protein Encoder Models

Official PyTorch Implementation of "Latent Diffusion Model Without Variational Autoencoder".

Potts model-based protein sequence design

PLM-interact: extending protein language models to predict protein-protein interactions.

A fully open source biomolecular structure prediction model based on AlphaFold3

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Codebase for NaFM: Pre-training a Foundation Model for Small-Molecule Natural Products

Open-source unified multimodal model

Fast protein structure searching or your money back

Message Passing Neural Networks for Molecule Property Prediction

Strategies for Pre-training Graph Neural Networks

A partially latent flow matching model for the joint generation of a protein’s amino acid sequence and full atomistic structure, including both the backbone and side chain.

Contrastive learning harmonizing protein language models and natural language models

ProTrek: illuminating the Protein Universe through Trimodal Protein Language Model

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Official code release for Ambient Protein Diffusion

Code for the paper "NovoMolGen: Rethinking Molecular Language Model Pretraining"

Wan: Open and Advanced Large-Scale Video Generative Models

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"

Code for InstructBioMol, implementing the Nature Machine Intelligence paper "Advancing Biomolecular Understanding and Design Following Human Instructions".