Andreas Loukas

Andreas Loukas

École Polytechnique Fédérale de Lausanne

H-index: 25

Europe-Switzerland

About Andreas Loukas

Andreas Loukas, With an exceptional h-index of 25 and a recent h-index of 24 (since 2020), a distinguished researcher at École Polytechnique Fédérale de Lausanne, specializes in the field of machine learning, geometric deep learning, protein design, drug discovery, generative models.

His recent articles reflect a diverse array of research interests and contributions to the field:

Protein Discovery with Discrete Walk-Jump Sampling

Exploring "dark matter" protein folds using deep learning

Towards Understanding and Improving GFlowNet Training

Learning protein family manifolds with smoothed energy-based models

AbDiffuser: Full-Atom Generation of In-Vitro Functioning Antibodies

Batched Predictors Generalize within Distribution

Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning

Conditional Diffusion with Less Explicit Guidance via Model Predictive Control

Andreas Loukas Information

University

Position

___

Citations(all)

3177

Citations(since 2020)

2860

Cited By

1071

hIndex(all)

25

hIndex(since 2020)

24

i10Index(all)

42

i10Index(since 2020)

34

Email

University Profile Page

École Polytechnique Fédérale de Lausanne

Google Scholar

View Google Scholar Profile

Andreas Loukas Skills & Research Interests

machine learning

geometric deep learning

protein design

drug discovery

generative models

Top articles of Andreas Loukas

Title

Journal

Author(s)

Publication Date

Protein Discovery with Discrete Walk-Jump Sampling

Nathan C Frey

Daniel Berenberg

Karina Zadorozhny

Joseph Kleinhenz

Julien Lafrance-Vanasse

...

2024

Exploring "dark matter" protein folds using deep learning

bioRxiv

Zander Harteveld

Alexandra Van Hall-Beauvais

Irina Morozova

Joshua Southern

Casper Alexander Goverde

...

2023

Towards Understanding and Improving GFlowNet Training

Max W Shen

Emmanuel Bengio

Ehsan Hajiramezanali

Andreas Loukas

Kyunghyun Cho

...

2023

Learning protein family manifolds with smoothed energy-based models

Nathan C Frey

Dan Berenberg

Joseph Kleinhenz

Isidro Hotzel

Julien Lafrance-Vanasse

...

2023

AbDiffuser: Full-Atom Generation of In-Vitro Functioning Antibodies

Karolis Martinkus

Jan Ludwiczak

Kyunghyun Cho

Wei-Ching Liang

Julien Lafrance-Vanasse

...

2023/11/13

Batched Predictors Generalize within Distribution

arXiv preprint arXiv:2307.09379

Andreas Loukas

Pan Kessel

2023/7/18

Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning

Mattia Atzeni

Mrinmaya Sachan

Andreas Loukas

2023/6/5

Conditional Diffusion with Less Explicit Guidance via Model Predictive Control

arXiv preprint arXiv:2210.12192

Max W Shen

Ehsan Hajiramezanali

Gabriele Scalia

Alex Tseng

Nathaniel Diamant

...

2022/10/21

A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences

NeurIPS 2022 - Workshop on AI for Science

Nataša Tagasovska

Nathan C Frey

Andreas Loukas

Isidro Hötzel

Julien Lafrance-Vanasse

...

2022/10/19

Deep sharpening of topological features for de novo protein design

Zander Harteveld

Joshua Southern

Michaël Defferrard

Andreas Loukas

Pierre Vandergheynst

...

2022/3/31

RosettaSurf—A surface-centric computational design approach

PLOS Computational Biology

Andreas Scheck

Stéphane Rosset

Michaël Defferrard

Andreas Loukas

Jaume Bonet

...

2022/3/16

On the generalization of learning algorithms that do not converge

Nisha Chandramoorthy

Andreas Loukas

Khashayar Gatmiry

Stefanie Jegelka

2022/10/31

SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

Karolis Martinkus

Andreas Loukas

Nathanaël Perraudin

Roger Wattenhofer

2022

Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions

Nikolaos Karalias

Joshua Robinson

Andreas Loukas

Stefanie Jegelka

2022/10/31

SQALER: Scaling question answering by decoupling multi-hop and logical reasoning

Advances in Neural Information Processing Systems

Mattia Atzeni

Jasmina Bogojeska

Andreas Loukas

2021/12/6

Partition and Code: learning how to compress graphs

Advances in Neural Information Processing Systems

Giorgos Bouritsas

Andreas Loukas

Nikolaos Karalias

Michael Bronstein

2021/12/6

Neural Extensions: Training Neural Networks with Set Functions

Nikolaos Karalias

Joshua David Robinson

Andreas Loukas

Stefanie Jegelka

2021/10/6

Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

ICML 2021

Yihe Dong

Jean-Baptiste Cordonnier

Andreas Loukas

2021/3/5

What training reveals about neural network complexity

Andreas Loukas

Marinos Poiitis

Stefanie Jegelka

2021

How hard is to distinguish graphs with graph neural networks?

Andreas Loukas

2020

See List of Professors in Andreas Loukas University(École Polytechnique Fédérale de Lausanne)

Co-Authors

H-index: 98
Kyunghyun Cho

Kyunghyun Cho

New York University

H-index: 76
Pierre Vandergheynst

Pierre Vandergheynst

École Polytechnique Fédérale de Lausanne

H-index: 71
Geert Leus

Geert Leus

Technische Universiteit Delft

H-index: 66
Pascal Frossard

Pascal Frossard

École Polytechnique Fédérale de Lausanne

H-index: 52
Stefan Schmid

Stefan Schmid

Universität Wien

H-index: 50
Martin Jaggi

Martin Jaggi

École Polytechnique Fédérale de Lausanne

academic-engine