Search · four archives
Search · four archives
22 papers · ranked by Valyu relevance
Alexander Vidal, Samy Wu Fung, Luis Tenorio, Stanley Osher + 1 more
'Levon Nurbekyan'] A normalizing flow (NF) is a mapping that transforms a chosen probability distribution to a normal distribution. Such flows are a common technique used for data generation and density estimation in machine learning and data science. The density estimate obtained with a NF requires a change of…
Vikram Voleti, Christopher C. Finlay, Adam M. Oberman, Christopher Pal
'Christopher Pal'] Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of Continuous Normalizing Flows (CNFs). Such models offer exact likelihood calculation, and invertible generation/density estimation. In this work we introduce a…
Alberto Cabezas, Louis Sharrock, Christopher Nemeth
Flows Authors: ['Alberto Cabezas' 'Louis Sharrock' 'Christopher Nemeth'] Continuous normalizing flows (CNFs) learn the probability path between a reference and a target density by modeling the vector field generating said path using neural networks. Recently, Lipman et al. [42] introduced a simple and inexpensive…
Hyeong‐Ju Kim, H. S. Lee, Woo Hyun Kang, Joun Yeop Lee + 1 more
Flow-based generative models are composed of invertible transformations between two random variables of the same dimension. Therefore, flow-based models cannot be adequately trained if the dimension of the data distribution does not match that of the underlying target distribution. In this paper, we propose SoftFlow, a…
Etrit Haxholli, Marco Lorenzi
While the neural ODE formulation of normalizing flows such as in FFJORD enables us to calculate the determinants of free form Jacobians in O(D) time, the flexibility of the transformation underlying neural ODEs has been shown to be suboptimal. In this paper, we present AFFJORD, a neural ODE-based normalizing flow which…
Phillip Lippe, Efstratios Gavves
Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a continuous space is inapplicable as categorical data has no intrinsic order. Instead, categorical data have complex and latent relations that…
Yikai Liu, Guang Lin, Ming Chen
Molecular dynamics (MD) simulations remain the standard tool for characterizing protein conformational landscapes, but their high computational cost limits large-scale and long-timescale applications. Recent generative models, especially diffusion-based approaches, provide promising alternatives by learning equilibrium…
Keegan Kelly, Lorena Piedras, Sukrit Rao, David J. Roth
Normalizing Flows (NFs) describe a class of models that express a complex target distribution as the composition of a series of bijective transformations over a simpler base distribution. By limiting the space of candidate transformations to diffeomorphisms, NFs enjoy efficient, exact sampling and density evaluation…
Jin Sub Lee, Philip M. Kim
Accurate prediction of protein side-chain conformations is necessary to understand protein folding, protein-protein interactions and facilitate de novo protein design. Here we apply torsional flow matching and equivariant graph attention to develop FlowPacker, a fast and performant model to predict protein side-chain…
Yikai Liu, Ming Chen, Guang Lin
Molecular dynamics (MD) provides a principled method for modeling equilibrium protein conformational energy landscapes, but its computational cost limits access to long timescales and larger protein systems. Recently, generative protein ensemble models and machine-learned coarse-grained force fields have emerged as…
Timothy A. Keller, Jorn W. T. Peters, Priyank Jaini, Emiel Hoogeboom + 2 more
'Patrick Forré' 'Max Welling'] Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework. Most proposed flow models therefore either restrict to a function class with easy evaluation of the Jacobian…
Nicholas J. Tustison, Brian B. Avants, Philip A. Cook, James C. Gee + 1 more
In modeling complex probability distributions, normalizing flows provide exact-likelihood, bijective mappings between empirical data and tractable latent spaces. Building on this foundation, latent-aligned multiview normalizing (LAMNr) flows leverage these salient properties to learn shared latent subspaces across…
Alexander Denker, Maximilian Schmidt, Johannes Leuschner, Peter Maass + 2 more
'Peter Maass' 'Fabiana Zama' 'Elena Loli Piccolomini'] Over recent years, deep learning methods have become an increasingly popular choice for solving tasks from the field of inverse problems. Many of these new data-driven methods have produced impressive results, although most only give point estimates for the…
Dustin Tran, Keyon Vafa, Kumar Krishna Agrawal, Laurent Dinh + 1 more
'Ben Poole'] While normalizing flows have led to significant advances in modeling highdimensional continuous distributions, their applicability to discrete distributions remains unknown. In this paper, we show that flows can in fact be extended to discrete events—and under a simple change-of-variables formula not…
Artem Ryzhikov, Maxim Borisyak, Andrey Ustyuzhanin, Denis Derkach + 1 more
'Donghyun Kim'] Anomaly detection is a challenging task that frequently arises in practically all areas of industry and science, from fraud detection and data quality monitoring to finding rare cases of diseases and searching for new physics. Most of the conventional approaches to anomaly detection, such as one-class…
Nathan Mancheun Lui, Max D Li, Matthew Ford
Deep generative models for molecular graphs offer a new avenue for property optimization in drug discovery. Optimizing differentiable models that generate molecular graphs is certainly faster, cheaper, and much more accessible than traditional methods of chemical synthesis. Recent advances in generative modeling have…
Josué Page Vizcaíno, Panagiotis Symvoulidis, Zeguan Wang, Jonas Jelten + 3 more
Real-time 3D fluorescence microscopy is crucial for the spatiotemporal analysis of live organisms, such as neural activity monitoring. The eXtended field-of-view light field microscope (XLFM), also known as Fourier light field microscope, is a straightforward, single snapshot solution to achieve this. The XLFM acquires…
Authors not listed
Inverse problems, where we seek the values of inputs to a model that lead to a desired set of outputs, are a challenges subset of problems in science and engineering. In this work we demonstrate the use of two generative AI methods to solve inverse problems. We compare this approach to two more conventional approaches…
Mike Boss, Michele Volpi, Lukas Roth
In this work, we investigate modeling plant traits over time using neural processes, a class of machine learning models that learn distributions over functions. Plant growth is an inherently stochastic process with complex dynamics measured mostly at irregular times throughout the growing seasons. While individual…
Saulo de Oliveira, Aryan Pedawi, Victor Kenyon, Henry van den Bedem
Commercially available, synthesis-on-demand virtual libraries contain upwards of trillions of readily synthesizable compounds for drug discovery campaigns. These libraries are a critical resource for rapid cycles of in silico discovery, property optimization and in vitro validation. However, as these libraries continue…
Yuanqi Du, Xian Liu, Shengchao Liu, Jieyu Zhang + 1 more
Discovering new structures in the chemical space is a long-standing challenge and has important applications to various fields such as chemistry, material science, and drug discovery. Deep generative models have been used in de novo molecule design to embed molecules in a meaningful latent space and then sample new…
Authors not listed
Multiscale modeling of complex chemical systems—ranging from polymers to biomolecules—requires coarse-grained (CG) techniques to bridge atomic-scale interactions with mesoscopic behavior. Traditional CG methods rely on handcrafted potentials, limiting their transferability across systems. We propose a…