Matthieu Kirchmeyer
YOU?
Author Swipe
View article: Unified all-atom molecule generation with neural fields
Unified all-atom molecule generation with neural fields Open
Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBind, a framework based on computer vision to generate target-…
View article: Lab-in-the-loop therapeutic antibody design with deep learning
Lab-in-the-loop therapeutic antibody design with deep learning Open
Therapeutic antibody design is a complex multi-property optimization problem with substantial promise for improvement with the application of machine-learning methods. Towards realizing that promise, we introduce “Lab-in-the-loop,” a new a…
View article: Score-based 3D molecule generation with neural fields
Score-based 3D molecule generation with neural fields Open
We introduce a new representation for 3D molecules based on their continuous atomic density fields. Using this representation, we propose a new model based on walk-jump sampling for unconditional 3D molecule generation in the continuous sp…
View article: Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design
Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design Open
Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model predicting the target property of interest. The model pred…
View article: Out-of-distribution Generalization in Deep Learning : Classification and Spatiotemporal Forecasting
Out-of-distribution Generalization in Deep Learning : Classification and Spatiotemporal Forecasting Open
Deep learning has emerged as a powerful approach for modelling static data like images and more recently for modelling dynamical systems like those underlying times series, videos or physical phenomena. Yet, neural networks were observed t…
View article: Continuous PDE Dynamics Forecasting with Implicit Neural Representations
Continuous PDE Dynamics Forecasting with Implicit Neural Representations Open
Effective data-driven PDE forecasting methods often rely on fixed spatial and / or temporal discretizations. This raises limitations in real-world applications like weather prediction where flexible extrapolation at arbitrary spatiotempora…
View article: Diverse Weight Averaging for Out-of-Distribution Generalization
Diverse Weight Averaging for Out-of-Distribution Generalization Open
Standard neural networks struggle to generalize under distribution shifts in computer vision. Fortunately, combining multiple networks can consistently improve out-of-distribution generalization. In particular, weight averaging (WA) strate…
View article: Generalizing to New Physical Systems via Context-Informed Dynamics Model
Generalizing to New Physical Systems via Context-Informed Dynamics Model Open
Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts. We propose a new framework for this key …
View article: Mapping conditional distributions for domain adaptation under generalized target shift
Mapping conditional distributions for domain adaptation under generalized target shift Open
We consider the problem of unsupervised domain adaptation (UDA) between a source and a target domain under conditional and label shift a.k.a Generalized Target Shift (GeTarS). Unlike simpler UDA settings, few works have addressed this chal…
View article: Mapping conditional distributions for domain adaptation under\n generalized target shift
Mapping conditional distributions for domain adaptation under\n generalized target shift Open
We consider the problem of unsupervised domain adaptation (UDA) between a\nsource and a target domain under conditional and label shift a.k.a Generalized\nTarget Shift (GeTarS). Unlike simpler UDA settings, few works have addressed\nthis c…
View article: Unsupervised domain adaptation with non-stochastic missing data
Unsupervised domain adaptation with non-stochastic missing data Open
View article: Conditional Generative Adversarial Networks for Regression
Conditional Generative Adversarial Networks for Regression Open
In recent years, impressive progress has been made in the design of implicit probabilistic models via Generative Adversarial Networks (GAN) and its extension, the Conditional GAN (CGAN). Excellent solutions have been demonstrated mostly in…
View article: Benchmarking Regression Methods: A comparison with CGAN
Benchmarking Regression Methods: A comparison with CGAN Open
In recent years, impressive progress has been made in the design of implicit probabilistic models via Generative Adversarial Networks (GAN) and its extension, the Conditional GAN (CGAN). Excellent solutions have been demonstrated mostly in…
View article: Regression with Conditional GAN
Regression with Conditional GAN Open
In recent years, impressive progress has been made in the design of implicit probabilistic models via Generative Adversarial Networks (GAN) and its extension, the Conditional GAN (CGAN). Excellent solutions have been demonstrated mostly in…
View article: Conformal Robotic Stereolithography
Conformal Robotic Stereolithography Open
Additive manufacturing by layerwise photopolymerization, commonly called stereolithography (SLA), is attractive due to its high resolution and diversity of materials chemistry. However, traditional SLA methods are restricted to planar subs…