Empowering legal justice with AI: A reinforcement learning SAC-VAE framework for advanced legal text summarization. by Xukang Wang, Ying Cheng Wu

“…We leverage a Variational Autoencoder (VAE) to condense the high-dimensional state space into a more manageable lower-dimensional feature space. …”
Get full text

Measuring heterogeneity in normative models as the effective number of deviation patterns. by Abraham Nunes, Thomas Trappenberg, Martin Alda

“…This finding is shown to be consistent across (A) application of a Gaussian process model to synthetic and real-world neuroimaging data, and (B) application of a variational autoencoder to well-understood database of handwritten images.…”
Get full text

VGE: Gene-Disease Association by Variational Graph Embedding by Peng Han, Xiangliang Zhang

“…We propose to learn a distribution for a disease or gene under the variational autoencoder framework, which enables disease-gene associations to be modeled by the Kullback-Leibler divergence. …”
Get full text

Symplectic encoders for physics-constrained variational dynamics inference by Kiran Bacsa, Zhilu Lai, Wei Liu, Michael Todd, Eleni Chatzi

“…Abstract We propose a new variational autoencoder (VAE) with physical constraints capable of learning the dynamics of Multiple Degree of Freedom (MDOF) dynamic systems. …”
Get full text

A Generative Verification Framework on Statistical Stability for Data-Driven Controllers by Suwon Lee

“…The proposed framework consists of three parts: the generative model, controller optimizer, and verification model. A variational autoencoder is used to classify and randomly generate data, and the generated data are used to train the controller. …”
Get full text

Variational Bayesian Approach to Condition-Invariant Feature Extraction for Visual Place Recognition by Junghyun Oh, Gyuho Eoh

“…Under the assumption that a latent representation of the variational autoencoder can be divided into condition-invariant and condition-sensitive features, a new structure of the variation autoencoder is proposed and a variational lower bound is derived to train the model. …”
Get full text

SeATAC: a tool for exploring the chromatin landscape and the role of pioneer factors by Wuming Gong, Nikita Dsouza, Daniel J. Garry

“…Here, SeATAC uses a conditional variational autoencoder model to learn the latent representation of ATAC-seq V-plots and outperforms MACS2 and NucleoATAC on six separate tasks. …”
Get full text

Applying interpolation-constrained autoencoders to world models approach reinforcement learning by Kevin Winata

“…World Models Approach Reinforcement Learning helps to tackle complex problems by breaking down the learning task to Vision Model, Memory Model, and Controller Model. Variational Autoencoder (VAE) is commonly used for Vision Model. …”
Get full text

Research on geomagnetic indoor high-precision positioning algorithm based on generative model by Shuai MA, Ke PEI, Huayan QI, Hang LI, Wen CAO, Hongmei WANG, Hailiang XIONG, Shiyin LI

“…Aiming at the current bottleneck of constructing a fine geomagnetic fingerprint library that required a lot of labor costs, two generative models called the conditional variational autoencoder and the conditional confrontational generative network were proposed, which could collect a small number of data samples for a given location, and generate pseudo-label fingerprints.At the same time, in order to solve the problem of low positioning accuracy of single-point geomagnetic fingerprints, a geomagnetic sequence positioning algorithm based on attention mechanism of convolutional neural network-gated recurrent unit was designed, which could effectively use the spatial and temporal characteristics of fingerprints to achieve precise positioning.In addition, a real-time, portable mobile terminal data collection and positioning system was also designed and built.The actual test shows that the proposed model can effectively construct the available geomagnetic fingerprint database, and the average error of the proposed algorithm can reach 0.16 m.…”
Get full text

Deep generative neural network for accurate drug response imputation by Peilin Jia, Ruifeng Hu, Guangsheng Pei, Yulin Dai, Yin-Ying Wang, Zhongming Zhao

“…Here, the authors develop a deep variational autoencoder model to compress gene signatures into latent vectors and accurately impute drug response.…”
Get full text

Generative models struggle with kirigami metamaterials by Gerrit Felsch, Viacheslav Slesarenko

“…We assess the performance of the four most popular generative models—the Variational Autoencoder (VAE), the Generative Adversarial Network (GAN), the Wasserstein GAN (WGAN), and the Denoising Diffusion Probabilistic Model (DDPM)—in generating kirigami structures. …”
Get full text

Airfoil Shape Generation and Feature Extraction Using the Conditional VAE-WGAN-gp by Kazuo Yonekura, Yuki Tomori, Katsuyuki Suzuki

“…A conditional VAE-WGAN-gp model, which couples the conditional variational autoencoder (VAE) and Wasserstein generative adversarial network with gradient penalty (WGAN-gp), is proposed for an airfoil generation method, and then, it is compared with the WGAN-gp and VAE models. …”
Get full text

Hybrid-Pursuit Strategies in Multiple Pursuer-Evader Games Using Reinforcement Learning by Yacun Guan, Wang Xu, Guohua Liu

“…This paper presents a comprehensive learning strategy for the collaborative pursuit of evaders by multiple pursuers in environments with dynamic obstacles. Utilizing a variational autoencoder framework for effective obstacle detection, we integrate the multiagent twin delayed deep deterministic policy gradient algorithm for training pursuers and the proximal policy optimization algorithm for evaders, forming a complete pursuit-evasion strategy. …”
Get full text

Research on geomagnetic indoor high-precision positioning algorithm based on generative model by Shuai MA, Ke PEI, Huayan QI, Hang LI, Wen CAO, Hongmei WANG, Hailiang XIONG, Shiyin LI

“…Aiming at the current bottleneck of constructing a fine geomagnetic fingerprint library that required a lot of labor costs, two generative models called the conditional variational autoencoder and the conditional confrontational generative network were proposed, which could collect a small number of data samples for a given location, and generate pseudo-label fingerprints.At the same time, in order to solve the problem of low positioning accuracy of single-point geomagnetic fingerprints, a geomagnetic sequence positioning algorithm based on attention mechanism of convolutional neural network-gated recurrent unit was designed, which could effectively use the spatial and temporal characteristics of fingerprints to achieve precise positioning.In addition, a real-time, portable mobile terminal data collection and positioning system was also designed and built.The actual test shows that the proposed model can effectively construct the available geomagnetic fingerprint database, and the average error of the proposed algorithm can reach 0.16 m.…”
Get full text

Neural network reconstructions for the Hubble parameter, growth rate and distance modulus by Isidro Gómez-Vargas, Ricardo Medel-Esquivel, Ricardo García-Salcedo, J. Alberto Vázquez

“…Furthermore, we introduce a first approach to generate synthetic covariance matrices through a variational autoencoder, using the systematic covariance matrix of the Type Ia supernova compilation.…”
Get full text

Extended Autoencoder for Novelty Detection with Reconstruction along Projection Pathway by Seung Yeop Shin, Han-joon Kim

“…The proposed model can be combined with variants of the autoencoder, such as a variational autoencoder or adversarial autoencoder. The effectiveness of the proposed model was evaluated across various novelty detection datasets. …”
Get full text

cDVAE: VAE-guided diffusion for particle accelerator beam 6D phase space projection diagnostics by Alexander Scheinker

“…The diffusion process is guided by a combination of scalar parameters and images that are converted to low-dimensional latent vector representation by a variational autoencoder (VAE). We demonstrate that conditional diffusion guided by a VAE (cDVAE) can accurately reconstruct all 15 of the unique 2D projections of a charged particle beam’s 6D phase space for the HiRES compact accelerator.…”
Get full text

New Physics Agnostic Selections For New Physics Searches by Woźniak Kinga Anna, Cerri Olmo, Duarte Javier M., Möller Torsten, Ngadiuba Jennifer, Nguyen Thong Q., Pierini Maurizio, Spiropulu Maria, Vlimant Jean-Roch

“…Prior to a search, each input event is preprocessed by the algorithm - a variational autoencoder (VAE). Based on the loss assigned to each event, input data can be split into a background control sample and a signal enriched sample. …”
Get full text

Weakly Supervised Representation Learning for Trauma Injury Pattern Discovery by Jin, Qixuan

“…We analyze 1,162,399 patients from the Trauma Quality Improvement Program with a disentangled variational autoencoder, weakly supervised by a latent-space classifier of auxiliary features. …”
Get full text

Improving generative modelling in VAEs using Multimodal Prior by Abrol, V, Sharma, P, Patra, A

“…In this paper we propose a conditional generative modelling (CGM) approach for unsupervised disentangled representation learning using variational autoencoder (VAE). CGM employs a multimodal/categorical conditional prior distribution in the latent space to learn global uncertainty in data by modelling the variations at local level. …”