Stars
Official Code for "Advancing Retrosynthesis with Retrieval-Augmented Graph Generation"
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Code for the paper "A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses" (ECCV 2020 - Spotlight)
[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)
Implementation of Learning Gradient Fields for Molecular Conformation Generation (ICML 2021).
Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).
PyTorch implementation of "PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters"
code for the paper "DiGress: Discrete Denoising diffusion for graph generation"
PyTorch implementation of "Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited"
A modular framework for neural networks with Euclidean symmetry
Course notes for CS228: Probabilistic Graphical Models.
Awesome Protein Representation Learning
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)
Implementation of Beyond Neural Scaling beating power laws for deep models and prototype-based models
Code and documentation to train Stanford's Alpaca models, and generate the data.
How Powerful are Spectral Graph Neural Networks
Welcome to the Physics-based Deep Learning Book v0.3 - the GenAI Edition