Spanish Abstract Meaning Representation: Annotation of a General Corpus by Shira Wein, Lucia Donatelli, Ethan Ricker, Calvin Engstrom, Alex Nelson, Leonie Harter, Nathan Schneider

“…Fine-tuning an AMR to-Spanish generation model with our annotations results in a BERTScore improvement of 8.8%, demonstrating initial utility of our work. …”
Get full text

Prompt Conditioned Batik Pattern Generation Using LoRA Weighted Diffusion Model With Classifier-Free Guidance by Rahmatulloh Daffa Izzuddin Wahid, Novanto Yudistira, Candra Dewi, Irawati Nurmala Sari, Dyanningrum Pradhikta, Fatmawati

“…Current research primarily focuses on batik classification, leaving a gap in the exploration of generative models for batik pattern creation. This paper investigates the application of text-to-image (T2I) generative models to synthesize batik motifs, leveraging latent diffusion models (LDM), Low-Rank Adaptation (LoRA), and classifier-free guidance. …”
Get full text

Session topic mining for interactive text based on conversational content by Jie PENG, Yongge SHI, Shengbao GAO

“…Traditional theme mining model generally digs out the document theme from the interactive text only.In order to explore the session topic and improve the universality of mining model,a kind of interactive text session topic generation model based on the content of the dialogue was put forward.Firstly,by analyzing the characteristics of interactive text and based on the concept of topic tree,a dialog spanning tree was defined with a five-layer structure.Based on this and LDA,the model of session topic generation(ST-LDA)was built.At last,Gibbs sampling method was adopted to deduce the ST-LDA and obtaining session topic and its distribution probability.The results show that the ST-LDA model can dig out a session topic effectively from the interactive text.Besides,the results can reduce the complexity of the classification algorithm and can be back to the theme—participants association.It also has a good universality.…”
Get full text

Generative steganography method based on auto-generation of contours by Zhili ZHOU, Meimin WANG, Gaobo YANG, Jianyu ZHU, Xingming SUN

“…To address the problems of limited hiding capacity and inaccurate information extraction in the existing generative steganography methods, a novel generative steganography method was proposed based on auto-generation of contours, which consisted of two main stages, such as the contour generation driven by secret information and the contour-to-image transformation.Firstly, the contour generation model was built based on long short term memory (LSTM) for secret information-driven auto-generation of object contours.Then, a contour-to-image reversible transformation model was constructed based on pix2pix network to obtain the stego-image, and the model also supported the reversible transformations from the stego-image to contours for secret information extraction.Experimental results demonstrate that the proposed method not only achieves high hiding capacity and accurate information extraction simultaneously, but also effectively resists the attacks by steganalysis tools.It performs much better than the state-of-the-art generative steganographic methods.…”
Get full text

Self-correcting complex semantic analysis method based on pre-training mechanism by Qing LI, Jiang ZHONG, Lili LI, Qi LI

“…In the process of knowledge service,in order to meet the fragmentation management needs of intellectualization,knowledge ability,refinement and reorganization content resources.Through deep analysis and mining of semantic hidden knowledge,technology,experience,and information,it broke through the existing bottleneck of traditional semantic parsing technology from Text-to-SQL.The PT-Sem2SQL based on the pre-training mechanism was proposed.The MT-DNN pre-training model mechanism combining Kullback-Leibler technology was designed to enhance the depth of context semantic understanding.A proprietary enhancement module was designed that captured the location of contextual semantic information within the sentence.Optimize the execution process of the generated model by the self-correcting method to solve the error output during decoding.The experimental results show that PT-Sem2SQL can effectively improve the parsing performance of complex semantics,and its accuracy is better than related work.…”
Get full text

Standalone and Minigrid-Connected Solar Energy Systems for Rural Application in Rwanda: An In Situ Study by Kuo-Chi Chang, Noel Hagumimana, Jishi Zheng, Godwin Norense Osarumwense Asemota, Jean De Dieu Niyonteze, Walter Nsengiyumva, Aphrodis Nduwamungu, Samuel Bimenyimana

“…In this paper, we develop a cost-effective power generation model for a solar PV system to power households in rural areas in Rwanda at a reduced cost. …”
Get full text

Finocyl Grain Design Using the Genetic Algorithm in Combination with Adaptive Basis Function Construction by Saeed Mesgari, Mehrdad Bazazzadeh, Alireza Mostofizadeh

“…An algorithm is developed beside the level-set code that prepares the initial grain configuration using a computer-aided design (CAD) to export generated models to the level-set code. The lumped method is used to perform internal ballistic analysis. …”
Get full text

Introducing <tt>ActiveInference.jl</tt>: A Julia Library for Simulation and Parameter Estimation with Active Inference Models by Samuel William Nehrer, Jonathan Ehrenreich Laursen, Conor Heins, Karl Friston, Christoph Mathys, Peter Thestrup Waade

“…To make active inference agents with Partially Observable Markov Decision Process (POMDP) generative models available to the growing research community using Julia, we re-implemented the pymdp library for Python. …”
Get full text

Machine Learning-Based Modeling of Hot Carrier Injection in 40 nm CMOS Transistors by Xhesila Xhafa, Ali Dogus Gungordu, Mustafa Berke Yelten

“…The model outcomes have been compared with the actual measurements, and the accuracy of the generated models has been demonstrated across the test data by providing the appropriate statistics metrics. …”
Get full text

Hybrid Quantum Cycle Generative Adversarial Network for Small Molecule Generation by Matvei Anoshin, Asel Sagingalieva, Christopher Mansell, Dmitry Zhiganov, Vishal Shete, Markus Pflitsch, Alexey Melnikov

“…This work develops an application of hybrid quantum generative models based on the integration of parameterized quantum circuits into known molecular generative adversarial networks and proposes quantum cycle architectures that improve model performance and stability during training. …”
Get full text

Spectral analysis of rotor current of induction motor as indicator of its effectiveness by V. L. Kodkin, A. S. Anikin, A. A. Baldenkov

“…It is proposed to use a spectral analysis of these currents, their main harmonics as the most accurate «display» of slip in an induction motor - as a method for assessing the quality of the motor torque generation. Modeling and experiments confirm the proposed theoretical propositions. …”
Get full text

Diffusion models for super-resolution microscopy: a tutorial by Harshith Bachimanchi, Giovanni Volpe

“…Diffusion models have emerged as a prominent technique in generative modeling with neural networks, making their mark in tasks like text-to-image translation and super-resolution. …”
Get full text

Similarities and differences between exosystem-model-based disturbance observer and model error compensator by Kana Shikada, Noboru Sebe

“…This observer is constructed against the augmented system model, which consists of nominal plant and disturbance-generating models. Ohnishi et al. proposed to cancel out the effect of uncertainties with its estimated disturbance. …”
Get full text

Molecular optimization using a conditional transformer for reaction-aware compound exploration with reinforcement learning by Shogo Nakamura, Nobuaki Yasuo, Masakazu Sekijima

“…Because of recent advances in deep learning, molecular generative models have been developed. However, the existing compound exploration models often disregard the important issue of ensuring the feasibility of organic synthesis. …”
Get full text

Integrating Sensor Technologies with Conversational AI: Enhancing Context-Sensitive Interaction Through Real-Time Data Fusion by Joseph C. Kush

“…Lastly, this article delves into the scientific principles supporting sensor technologies, data processing methods, and their fusion with generative models such as ChatGPT to develop adaptable, dynamic systems that engage with humans intelligently in real time. …”
Get full text

Design and Application of Reliability Calculation Program Based on Secondary Development of ABAQUS by ZOU Hong, WU Jian, XU Zhichun, YANG Li

“…As a kind of finite element analysis software,ABAQUS is widely used in nonlinear simulation field,but there is no universal and mature reliability calculation module.Therefore,it is necessary to establish a general reliability calculation program for Monte Carlo simulation based on finite element model to meet the automation requirements of reliability calculation of various structures in ABAQUS.This paper firstly puts forward the design idea and main functions of reliability calculation program in ABAQUS,including random number generation,model batch building,automatic result extraction and so on;then,develops the pre-processing and post-processing modules of ABAQUS with Python language for modularizing the main functions of the program;finally,introduces the application method of this reliability calculation program in detail taking the reliability calculation process of the finite element model of a simply supported steel truss bridge as an example.This reliability calculation program can effectively improve the degree of automation in the process of structural reliability calculation,and reduce the calculation time,which has great reference value in engineering application.…”
Get full text

The Generalization Complexity Measure for Continuous Input Data by Iván Gómez, Sergio A. Cannas, Omar Osenda, José M. Jerez, Leonardo Franco

“…Finally, we demonstrate the application of the introduced complexity measure, by using the generated model, to the problem of estimating an adequate neural network architecture for real-world data sets.…”
Get full text

Advancements in Vision–Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement Techniques by Lijie Tao, Haokui Zhang, Haizhao Jing, Yu Liu, Dawei Yan, Guoting Wei, Xizhe Xue

“…Differing from previous AI approaches that generally formulated different tasks as discriminative models, VLMs frame tasks as generative models and align language with visual information, enabling the handling of more challenging problems. …”
Get full text

Structural model of a bacterial focal adhesion complex by Christian Cambillau, Tâm Mignot

“…In this study, we utilize AlphaFold to generate models based on the known interactions and dynamics of gliding motility proteins. …”
Get full text

Robust Framework to Combine Diverse Classifiers Assigning Distributed Confidence to Individual Classifiers at Class Level by Shehzad Khalid, Sannia Arshad, Sohail Jabbar, Seungmin Rho

“…An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. …”
Get full text