a collection of awesome autoregressive visual generation models

Graph Diffusion Convolution, as proposed in "Diffusion Improves Graph Learning" (NeurIPS 2019)

Listing of papers about machine learning for proteins.

List of papers about Proteins Design using Deep Learning

Sequence-Structure-Surface Model for Protein Fitness Prediction (S3F)

Official repository for the ProteinGym benchmarks

A curated list for awesome discrete diffusion models resources.

Official Implemetation of DPLM (ICML'24) - Diffusion Language Models Are Versatile Protein Learners

All graph/GNN papers accepted at NeurIPS 2024.

PyGCL: A PyTorch Library for Graph Contrastive Learning

Augmenting zero-shot mutant prediction by retrieval-based logits fusion.

Fast protein backbone generation with SE(3) flow matching.

Foldseek enables fast and sensitive comparisons of large structure sets.

[NeurIPS 2023, Spotlight] Rank-N-Contrast: Learning Continuous Representations for Regression

List of papers on ICLR 2024

Polynormer: Polynomial-Expressive Graph Transformer in Linear Time

All graph/GNN papers accepted at the International Conference on Machine Learning (ICML) 2024.

Full-Atom Peptide Design based on Multi-modal Flow Matching (ICML 2024)

Joint sequence and structure generation with RoseTTAFold sequence space diffusion

从零手搓Flow Matching（Rectified Flow）

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

A powerful and flexible machine learning platform for drug discovery

Code for TKDE paper "Self-supervised learning on graphs: Contrastive, generative, or predictive"

Code of "Graph Contrastive Learning with Stable and Scalable Spectral Encoding"