相关论文: STAR-VAE: Latent Variable Transformers for Scalabl…

Predicting molecular conformations (or 3D structures) from molecular graphs is a fundamental problem in many applications. Most existing approaches are usually divided into two steps by first predicting the distances between atoms and then…

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

Variational autoencoders (VAEs) are a popular generative model used to approximate distributions. The encoder part of the VAE is used in amortized learning of latent variables, producing a latent representation for data samples. Recently,…

Comprehensive and unambiguous identification of small molecules in complex samples will revolutionize our understanding of the role of metabolites in biological systems. Existing and emerging technologies have enabled measurement of…

Disordered materials such as glasses, unlike crystals, lack long range atomic order and have no periodic unit cells, yielding a high dimensional configuration space with widely varying properties. The complexity not only increases…

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…

As big spatial data becomes increasingly prevalent, classical spatiotemporal (ST) methods often do not scale well. While methods have been developed to account for high-dimensional spatial objects, the setting where there are exceedingly…

Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior such as standard…

Cancer is a primary cause of human death, but discovering drugs and tailoring cancer therapies are expensive and time-consuming. We seek to facilitate the discovery of new drugs and treatment strategies for cancer using variational…

As deep Variational Auto-Encoder (VAE) frameworks become more widely used for modeling biomolecular simulation data, we emphasize the capability of the VAE architecture to concurrently maximize the timescale of the latent space while…

Given an image dataset, we are often interested in finding data generative factors that encode semantic content independently from pose variables such as rotation and translation. However, current disentanglement approaches do not impose…

Recent advances in artificial intelligence have propelled the development of innovative computational materials modeling and design techniques. Generative deep learning models have been used for molecular representation, discovery, and…

Variational autoencoders (VAEs) are powerful generative models with the salient ability to perform inference. Here, we introduce a quantum variational autoencoder (QVAE): a VAE whose latent generative process is implemented as a quantum…

Bayesian optimisation in the latent space of a Variational AutoEncoder (VAE) is a powerful framework for optimisation tasks over complex structured domains, such as the space of scientifically interesting molecules. However, existing…

We develop a semi-supervised variational autoencoder (SSVAE) framework to reconstruct and generate neutron star (NS) equations of state (EOS). The SSVAE consists of an encoder network that maps high-dimensional EOS data into a…

In this paper, we introduce ControlVAE, a novel model-based framework for learning generative motion control policies based on variational autoencoders (VAE). Our framework can learn a rich and flexible latent representation of skills and a…

Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…

A major challenge in quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional…

Based on the traditional VAE, a novel neural network model is presented, with the latest molecular representation, SELFIES, to improve the effect of generating new molecules. In this model, multi-layer convolutional network and Fisher…

Controllable data generation aims to synthesize data by specifying values for target concepts. Achieving this reliably requires modeling the underlying generative factors and their relationships. In real-world scenarios, these factors…