Institute for Machine Learning, Johannes Kepler University Linz

hopfield-layers

Hopfield Networks is All You Need

DeepRC

DeepRC: Immune repertoire classification with attention-based deep massive multiple instance learning

clamp

Code for the paper Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language

HopCPT

Conformal Prediction for Time Series with Modern Hopfield Networks

helm

L2M

Learning to Modulate pre-trained Models in RL (Decision Transformer, LoRA, Fine-tuning)

mhn-react

Modern Hopfield Network (MHN) for template relevance prediction

hyper-dti

HyperPCM: Robust task-conditioned modeling of drug-target interactions

cloome

MAE-CT

MIM-Refiner

A Contrastive Learning Boost from Intermediate Pre-Trained Representations

OfflineRL

quam

Quantification of Uncertainty with Adversarial Models

UPT

Code for the paper Universal Physics Transformers

semantic-image-text-alignment

hopfield-boosting

subgd

Code for "Few-Shot Learning by Dimensionality Reduction in Gradient Space"

mgenerators-failure-modes

Shows some of the ways molecule generation and optimization can go wrong

MHNfs

vnegnn

hti-cnn

VAG-CO

bgnn

GNN-VPA

A Variance-Preserving Aggregation Strategy for Graph Neural Networks

convex-init

Code for Principled Weight Initialisation for Input-Convex Neural Networks

DIffUCO

ml-jku.github.io

Repository for the website of Institute for Machine Learning, Linz.

autoregressive_activity_prediction

This repo includes code for the autoregressive activity prediction for low-data drug discovery manuscript

diverse-hits

Code accompanying our paper on diversity-based comparison of goal-directed generators

universal-physics-transformer

Universal Physics Transformer