检索结果-内蒙古大学图书馆

Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation 39

学校读者我要写书评

暂无评论

Harnessing Multimodal Large Language Models for Multimodal S...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Yuyang Zheng, Zhi Shen, Yishan Wang, Tianshu Zhang, Hengruo Zhu, Peijun Yu, Runlong Zhang, Kai Xiong, Hui Department of Management Science and Information Systems Rutgers University United States School of Data Science University of Science and Technology of China China Department of Applied Mathematics and Computational Science University of Pennsylvania United States Bytedance Inc. China School of Computer Science Georgia Institute of Technology United States Department of Computer Science University of Pittsburgh United States China

ISBN: (纸本)157735897X

Recent advances in Large Language Models (LLMs) have demonstrated significant potential in the field of Recommendation Systems (RSs). Most existing studies have focused on converting user behavior logs into textual prompts and leveraging techniques such as prompt tuning to enable LLMs for recommendation tasks. Meanwhile, research interest has recently grown in multimodal recommendation systems that integrate data from images, text, and other sources using modality fusion techniques. This introduces new challenges to the existing LLM-based recommendation paradigm which relies solely on text modality information. Moreover, although Multimodal Large Language Models (MLLMs) capable of processing multi-modal inputs have emerged, how to equip MLLMs with multi-modal recommendation capabilities remains largely unexplored. To this end, in this paper, we propose the Multimodal Large Language Model-enhanced Sequential Multimodal Recommendation (MLLM-MSR) model. To capture the dynamic user preference, we design a two-stage user preference summarization method. Specifically, we first utilize an MLLM-based item-summarizer to extract image feature given an item and convert the image into text. Then, we employ a recurrent user preference summarization generation paradigm to capture the dynamic changes in user preferences based on an LLM-based user-summarizer. Finally, to enable the MLLM for multi-modal recommendation task, we propose to fine-tune a MLLM-based recommender using Supervised Fine-Tuning (SFT) techniques. Extensive evaluations across various datasets validate the effectiveness of MLLM-MSR, showcasing its superior ability to capture and adapt to the evolving dynamics of user preferences. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

Solar radio bursts observations by Egypt- Alexandria CALLISTO spectrometer: First results

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Minta, F.N. Nozawa, S.I. Kozarev, K. Elsaid, A. Mahrous, A. Department of Space Environment Institute of Basic and Applied Sciences Egypt-Japan University of Science and Technology Alexandria21934 Egypt Department of Science Ibaraki University 2-1-1 Bunkyo Ibaraki Mito310-8512 Japan Institute of Astronomy with National Astronomical Observatory Bulgarian Academy of Sciences Sofia Bulgaria Department of Applied and Computational Mathematics Institute of Basic and Applied Sciences Egypt-Japan University of Science and Technology Alexandria21934 Egypt Mathematics & Engineering Physics Department Faculty of Engineering Mansoura University MansouraPO 35516 Egypt

The newly installed CALLISTO spectrometer, hosted by the Department of Space Environment, institute of Basic and applied sciences- EJUST, commenced operation on August 14, 2021. The system contains a cross dipole long-wavelength array antenna with high sensitivity to monitor solar radio transients. Its antenna was strategically positioned and appeared to be in the center of the CALLISTO network of spectrometers. Moreover, in the northern section of Africa, the Egypt-Alexandria CALLISTO and ALGERIA-CRAAG stations are the only ones operating. There are no stations in the West African region, while stations in the eastern part of Africa are not working. Thus, Egypt- Alexandria station serves as a reference for other stations within the e-CALLISTO network. Despite the low solar activity, the instrument detected several solar radio bursts not limited to type II, type III, and type V. A vigorous case study was conducted on two selected radio burst events to validate the authenticity of the recorded events. Other solar radio stations at different geographical locations recorded all the radio bursts detected by the spectrometer. The case study included brief analyses that indicated a type II radio burst observed on October 09, 2021, between 06:30 and 07:00 UT, was associated with an M1.6 solar flare located at N18E08 within NOAA-AR 12882 and a CME with a shock front speed of ~978 km/s. However, the type III radio burst is neither CME nor solar flare associated. These analyses examine the instrument's capacity to provide real-time solar radio transient data 24 hours a day to mitigate the challenges of data gaps faced in the African continent. Hence, the instrument has become an integral part of space weather monitoring and forecasting over the region and other parts of the globe. © 2023, CC BY-NC-ND.

关键词： Solar energy

Comparison of Lattice Boltzmann,Finite Element and Volume of Fluid Multicomponent Methods for Microfluidic Flow Problems and the Jetting of Microdroplets

学校读者我要写书评

暂无评论

Communications in Computational physics 2023年第3期33卷 912-936页

作者： Karun P.N.datadien Gianluca Di Staso Christian Diddens Herman M.A.Wijshoff Federico Toschi Department of Applied Physics and Science Education Eindhoven University of Technology5600MB EindhovenNetherlands FLOW Matters Consultancy B.V. 5612AEEindhovenThe Netherlands Physics of Fluids group Department of Science and TechnologyMesa+InstituteMax Planck Center for Complex Fluid Dynamics and J.M.Burgers Centre for Fluid DynamicsUniversity of TwenteP.O.Box 2177500 AE EnschedeThe Netherlands Canon Production Printing Netherlands B.V. 5914 HHVenloThe Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology5600MB EindhovenNetherlands Istituto per le Applicazioni del Calcolo Consiglio Nazionale delle Ricerche00185 RomeItaly.

We show that the lattice Boltzmann method(LBM)based color-gradient model with a central moments formulation(CG-CM)is capable of accurately simulating the droplet-on-demand inkjetting process on a micrometer length scale by comparing it to the Arbitrary Lagrangian Eulerian Finite Element Method(ALE-FEM).A full jetting cycle is simulated using both CG-CM and ALE-FEMand results are quantitatively compared by measuring the ejected ink velocity,volume and contraction *** also show that the individual relevant physical phenomena are accurately captured by considering three test-cases;droplet oscillation,ligament contraction and capillary *** first two cases test accuracy for a dynamic system where surface tension is the driving force and the third case is designed to test wetting boundary *** the first two cases we also compare the CG-CM and ALE-FEM results to Volume of Fluid(VOF)*** of the three methods shows close agreement when compared to each other and analytical solutions,where *** we demonstrate that asymmetric jetting is achievable using 3D CG-CM simulations utilizing asymmetric wetting conditions inside the *** allows for systematic investigation into the physics of asymmetric jetting,*** to jet-nozzle manufacturing imperfections or due to other disturbances.

关键词： Lattice Boltzmann method multiphase flow multicomponent flow inkjet printing

WANCO: WEAK ADVERSARIAL NETWORKS FOR CONSTRAINED OPTIMIZATION PROBLEMS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bao, Gang Wang, Dong Zou, Boyi School of Mathematical Sciences Zhejiang University Zhejiang China School of Science and Engineering The Chinese University of Hong Kong Guangdong Shenzhen518172 China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data Guangdong518172 China

This paper focuses on integrating the networks and adversarial training into constrained optimization problems to develop a framework algorithm for constrained optimization problems. For such problems, we first transform them into minimax problems using the augmented Lagrangian method and then use two (or several) deep neural networks(DNNs) to represent the primal and dual variables respectively. The parameters in the neural networks are then trained by an adversarial process. The proposed architecture is relatively insensitive to the scale of values of different constraints when compared to penalty based deep learning methods. Through this type of training, the constraints are imposed better based on the augmented Lagrangian multipliers. Extensive examples for optimization problems with scalar constraints, nonlinear constraints, partial differential equation constraints, and inequality constraints are considered to show the capability and robustness of the proposed method, with applications ranging from Ginzburg-Landau energy minimization problems, partition problems, fluid-solid topology optimization, to obstacle problems. Copyright © 2024, The Authors. All rights reserved.

关键词： Constrained optimization

Not all spacetime coordinates for general-relativistic ray tracing are created equal

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bozzola, Gabriele Chan, Chi-Kwan Paschalidis, Vasileios Department of Astronomy University of Arizona TucsonAZ United States Data Science Institute University of Arizona TucsonAZ United States Program in Applied Mathematics University of Arizona TucsonAZ United States Department of Physics University of Arizona TucsonAZ United States

Models for the observational appearance of astrophysical black holes rely critically on accurate general-relativistic ray tracing and radiation transport to compute the intensity measured by a distant observer. In this paper, we illustrate how the choice of coordinates and initial conditions affect this process. In particular, we show that propagating rays from the camera to the source leads to different solutions if the spatial part of the momentum of the photon points towards the horizon or away from it. In doing this, we also show that coordinates that are well suited for numerical General-Relativistic MagnetoHydroDynamic (GRMHD) simulations are typically not optimal for generic ray tracing. We discuss the implications for black-hole images and show that radiation transport in optimal and non-optimal spacetime coordinates lead to the same images up to numerical errors and algorithmic choices. Copyright © 2023, The Authors. All rights reserved.

关键词： Ray tracing

Taming numerical imprecision by adapting the KL divergence to negative probabilities

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pfahler, Simon Georg, Peter Schill, Rudolf Klever, Maren Grasedyck, Lars Spang, Rainer Wettig, Tilo Department of Physics University of Regensburg Regensburg93040 Germany Department of Biosystems and Engineering ETH Zürich Basel4056 Switzerland Institute for Geometry and Applied Mathematics RWTH Aachen Aachen52062 Germany Department of Informatics and Data Science University of Regensburg Regensburg93040 Germany

The Kullback-Leibler (KL) divergence is frequently used in data science. For discrete distributions on large state spaces, approximations of probability vectors may result in a few small negative entries, rendering the KL divergence undefined. We address this problem by introducing a parameterized family of substitute divergence measures, the shifted KL (sKL) divergence measures. Our approach is generic and does not increase the computational overhead. We show that the sKL divergence shares important theoretical properties with the KL divergence and discuss how its shift parameters should be chosen. If Gaussian noise is added to a probability vector, we prove that the average sKL divergence converges to the KL divergence for small enough noise. We also show that our method solves the problem of negative entries in an application from computational oncology, the optimization of Mutual Hazard Networks for cancer progression using tensor-train approximations. Copyright © 2023, The Authors. All rights reserved.

关键词： Tensors

Dynamics of an atom cavity field system in interacting Fock space

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Das, P.K. Chatterjee, Arpita Physics and Applied Mathematics Unit Indian Statistical Institute 203 B. T. Road Kolkata700108 India Department of Mathematics J. C. Bose University of Science and Technology YMCA Faridabad India

In this paper, we investigate one-time passing of a V-type three-level atom through a single-mode interacting field in a cavity. We extend the idea of elementary Jaynes-Cummings model by assuming that the field vector belongs to interacting Fock space. In the process, we arrive at a state vector which will be analyzed to study the nonclassicality of the evolved state of the *** Codes 81V80 © 2023, CC BY.

关键词： Atoms

A GENERALIZED EXPANSION METHOD FOR COMPUTING LAPLACE-BELTRAMI EIGENFUNCTIONS ON MANIFOLDS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Turner, Jackson C. Cherkaev, Elena Wang, Dong Department of Applied Physics and Applied Mathematics Columbia University New York City10027 United States Department of Mathematics University of Utah Salt Lake City84112 United States School of Science and Engineering The Chinese University of Hong Kong Guangdong Shenzhen518172 China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data Guangdong518172 China

Eigendecomposition of the Laplace-Beltrami operator is instrumental for a variety of applications from physics to data science. We develop a numerical method of computation of the eigenvalues and eigenfunctions of the Laplace-Beltrami operator on a smooth bounded domain based on the relaxation to the Schrödinger operator with finite potential on a Riemannian manifold and projection in a special basis. We prove spectral exactness of the method and provide examples of calculated results and applications, particularly, in quantum billiards on *** Codes 65N25m, 47A70, 65N85, 35J05 © 2022, CC BY.

关键词： Eigenvalues and eigenfunctions

JARVIS-Leaderboard:a large scale benchmark of materials design methods

学校读者我要写书评

暂无评论

npj Computational Materials 2024年第1期10卷 2280-2296页

作者： Kamal Choudhary Daniel Wines Kangming Li Kevin F.Garrity Vishu Gupta Aldo H.Romero Jaron T.Krogel Kayahan Saritas Addis Fuhr Panchapakesan Ganesh Paul R.C.Kent Keqiang Yan Yuchao Lin Shuiwang Ji Ben Blaiszik Patrick Reiser Pascal Friederich Ankit Agrawal Pratyush Tiwary Eric Beyerle Peter Minch Trevor David Rhone Ichiro Takeuchi Robert B.Wexler Arun Mannodi-Kanakkithodi Elif Ertekin Avanish Mishra Nithin Mathew Mitchell Wood Andrew Dale Rohskopf Jason Hattrick-Simpers Shih-Han Wang Luke E.K.Achenie Hongliang Xin Maureen Williams Adam J.Biacchi Francesca Tavazza Material Measurement Laboratory National Institute of Standards and TechnologyGaithersburgMD20899USA Department of Materials Science and Engineering University of Toronto27 King’s College CirTorontoONCanada Department of Electrical and Computer Engineering Northwestern UniversityEvanstonIL 60208USA Lewis-Sigler Institute for Integrative Genomics Princeton UniversityPrincetonNJ 08544USA Ludwig Institute for Cancer Research Princeton UniversityPrincetonNJ 08544USA Department of Physics and Astronomy West Virginia UniversityMorgantownWV 26506USA Materials Science and Technology Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Center for Nanophase Materials Science Oak Ridge National LaboratoryOak RidgeTN 37831USA Computational Sciences and Engineering Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Department of Computer Science and Engineering Texas A&M UniversityCollege StationTX 77843USA Globus University of ChicagoChicagoIL 60637USA Data Science and Learning Division Argonne National LabLemontIL 60439USA Institute of Nanotechnology Karlsruhe Institute of TechnologyKaiserstraße 1276131 KarlsruheGermany Institute of Theoretical Informatics Karlsruhe Institute of TechnologyKaiserstraße 1276131 KarlsruheGermany Department of Chemistry and Biochemistry and Institute for Physical Science and Technology University of MarylandCollege ParkMD 20742USA Department of Physics Applied Physics and AstronomyRensselaer Polytechnic InstituteTroyNY12180USA Department of Materials Science and Engineering University of MarylandCollege ParkMD20742USA Department of Chemistry and Institute of Materials Science and Engineering Washington University in St.LouisSt.LouisMO63130USA School of Materials Engineering Purdue UniversityWest LafayetteIN47907USA Department of Mechanical Science and Engineering University of Illinois Urbana-ChampaignUrbanaIllinois 61801USA Materials Research Laboratory University of Illinois Urbana-ChampaignUrbanaIL 61801USA Theore

Lack of rigorous reproducibility and validation are significant hurdles for scientific development across many *** science,in particular,encompasses a variety of experimental and theoretical approaches that require careful *** efforts have been developed previously to mitigate these ***,a comprehensive comparison and benchmarking on an integrated platform with multiple data modalities with perfect and defect materials data is still *** work introduces JARVIS-Leaderboard,an open-source and community-driven platform that facilitates benchmarking and enhances *** platform allows users to set up benchmarks with customtasks and enables contributions in the form of dataset,code,and meta-data *** cover the following materials design categories:Artificial Intelligence(AI),Electronic Structure(ES).

关键词： rigorous perfect enable