-
Text-to-image models can generate personalized images with unprecedented freedom by using a pseudo-word learned from a few images, using a novel technique called textual inversion. It is conceivable that, in the spirit of federated learning, multiple users wis…
crossref
Sijia Chen, Ningxin Su, Baochun Li
2024-09-26T17:41:00Z
置信度 0.70
-
Wireless charging efficiency in electric vehicles (EVs) relies on proper alignment of the vehicle's wireless receiver to its wireless power transfer charging pad, which has a significant impact on the performance and safety of an EV's wireless power transfer, …
crossref
T. Mani, R. Yasmin, J. Dharani, K. Yugin Mary 等
2026-06-11T19:58:03Z
置信度 0.70
-
crossref
Victoria Vesna
2023-10-21T03:16:57Z
置信度 0.70
-
crossref
Bibin Xavier
2024-06-13T04:01:32Z
置信度 0.70
-
The confluence of increased processing power, complex algorithms and vast databases has created a new era in banking, where robots are not simply tools but intelligent partners. Artificial intelligence (AI) has become an integral part of financial technology, …
crossref
Hari Prasad Josyula
2024-12-01T05:32:11Z
置信度 0.70
-
In the rapidly advancing domain of technology, Generative AI is emerging as a pivotal force, steering us into a new epoch of innovation and creativity. This branch of AI, renowned for its capability to create and innovate, is moving beyond traditional realms o…
crossref
Irena Cronin
2024-05-21T21:01:21Z
置信度 0.70
-
Recommendations for analysis of pathology image search algorithms and a road map for clinical adoption are provided.
crossref
Richard J. Chen, Faisal Mahmood
2024-04-25T13:00:30Z
置信度 0.70
-
Abstract According to philosophers and scientists in artificial intelligence (AI), future autonomous agents with general AI constitute an existential risk to humanity. This paper leverages results from neuroscience to propose tools with general AI and no exist…
crossref
Kjell Jørgen Hole
2023-03-07T12:02:57Z
置信度 0.70
-
crossref
James D. Miller
2025-03-21T13:28:09Z
置信度 0.70
-
crossref
2024-05-07T17:18:45Z
置信度 0.70
-
The discrimination problem in seismology aims to accurately classify different underground source types based on local, regional or teleseismic observations of ground motion. Typical discriminant approaches are rooted in fundamental, physics-based differences …
crossref
Marlon Ramos, Rigobert Tibi, Christopher Young, Erica Emry
2024-09-26T20:58:03Z
置信度 0.70
-
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent works have focused on source-free UDA, where only target data is available. This is challenging as models rely on noisy pseudo-la…
crossref
Chrisantus Eze, Christopher Crick
2025-03-04T18:39:11Z
置信度 0.70
-
crossref
Junfei HU, Mathilde Hutin, Liesbeth Degand
2024-04-25T13:17:50Z
置信度 0.70
-
Accurately detecting distant evolutionary relationships between proteins remains an ongoing challenge in bioinformatics. Search methods based on primary sequence struggle to accurately detect homology between sequences with less than 20% amino acid identity. P…
crossref
Alan M Moses
2024-02-26T11:27:24Z
置信度 0.70
-
crossref
Sofia Rosero Abad, Rudi Bekkers, Emilio Raiteri
2024-05-30T11:39:10Z
置信度 0.70
-
A data warehouse is built to address the strategic needs of an organization. Organizations allocate considerable resources to data warehouse projects, but there has been very little discussion on how to achieve a strategic alignment between the data warehouse …
crossref
2020-12-22T20:00:24Z
置信度 0.70
-
crossref
Tao Lin, GanZhi Luo, Wei Wang, WenYao Li
2024-10-10T12:39:30Z
置信度 0.70
-
Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility function, will inevitably be…
crossref
Paulo Garcia
2024-09-10T16:02:45Z
置信度 0.70
-
crossref
Khaled ELKarazle, Valliappan Raman, Patrick Then, Caslon Chua
2024-03-05T13:02:53Z
置信度 0.70
-
crossref
Paul J. Barr, Robert Gramling, Soroush Vosoughi
2024-10-17T10:01:06Z
置信度 0.70
-
<span>This book explores the use of artificial intelligence by intelligence services around the world and its critical role in intelligence analysis, defense, and national security. Intelligence services play a crucial role in national security, and the …
crossref
Nicolae Sfetcu
2024-12-06T19:25:07Z
置信度 0.70
-
crossref
Jacques Bughin
2024-08-08T15:02:23Z
置信度 0.70
-
This study was conducted to determine the influence of entrepreneurial interest on Surabaya State University students after participating in the entrepreneurial student development program (P2MW) through locus of control as an intervening variable. This study …
crossref
Rival Dani Ardiansyah, Saino Saino
2024-08-06T23:35:02Z
置信度 0.70
-
This study began with the aim of addressing global healthcare challenges—aging populations, resource shortages, and regional disparities—by integrating artificial intelligence (AI) into telemedicine. The objective was to explore the application of AI-driven te…
crossref
Ai Deng, Seo Han Sok
2025-01-15T04:49:11Z
置信度 0.70
-
We provide evidence that the development and adoption of Generative AI is driving a significant technological shift for firms and for financial research.We review the literature on the impact of ChatGPT on firm value and provide directions for future research …
crossref
Andrea Eisfeldt, Gregor Schubert
2024-10-29T00:18:02Z
置信度 0.70
-
Thank you for choosing this book. Getting Started with Azure OpenAI is my fifth book and third book about Microsoft Azure. In my previous two Azure books, I focused on Microsoft Azure container services (AKS, ACR, Docker, etc.) and how to use infrastructure-as…
crossref
Shimon Ifrah
2024-08-28T10:02:49Z
置信度 0.70
-
model may be producible to help de-blend losses between machines. Work is underway as part of the Fermilab Real-time Edge AI for Distributed Systems Project (READS) to develop a ML empowered system that collects streamed BLM data and additional machine reading…
crossref
Kyle Hazelwood
2024-02-04T03:44:06Z
置信度 0.70
-
Cancer care often involves making complex medical decisions within a challenging environment: a balkanized medical system of many specialists, information overload and obsolescence, limited time with doctors, and siloed data. New AI tools can enable patients a…
crossref
Frank Nothaft, Brad Power
2024-08-30T06:29:10Z
置信度 0.70
-
Deep Learning (DL) frameworks such as PyTorch and TensorFlow include runtime infrastructures responsible for executing trained models on target hardware, managing memory, data transfers, and multi-accelerator execution, if applicable. Additionally, it is a com…
crossref
Negar Alizadeh, Fernando Castor
2024-06-11T17:28:38Z
置信度 0.70
-
crossref
2025-07-17T11:26:39Z
置信度 0.70
-
crossref
Jingyuan Duan, Zhao Kang, Ling Tian, Yichen Xin
2024-08-14T11:00:27Z
置信度 0.70
-
Abstract. Wind farm layout optimization involves placing wind turbines in a defined domain to minimize the expected production losses due to wake effects within the wind farm. Because of navigational regulations, tenders for offshore wind farms often impose so…
crossref
Paul Malisani, Tristan Bartement, Pauline Bozonnet
2024-10-17T04:51:52Z
置信度 0.70
-
Our benchmarking Llama 3 for Chinese news summarization is a novel approach that integrates cultural and ethical considerations into model evaluation, significantly enhancing the relevance and acceptability of the generated content. The study employs a compreh…
crossref
Tianxuan Lu, Jin Hu, Pingping Chen
2024-06-03T10:11:38Z
置信度 0.70
-
crossref
Xitong Luo, Lei Zhang, Yafeng Pan
2024-11-11T16:37:24Z
置信度 0.70
-
1. Prime Ministers Museum and Library, New Delhi [henceforth PMML], Jawaharlal Nehru Papers [henceforth JN], file 306 part I, Note on Proposed Afro-Asian C
crossref
Andrea Benvenuti
2024-11-21T04:38:48Z
置信度 0.70
-
Progress on Superhuman Theorem Proving? Steve Omohundro, Co-Founding Editor Harmonic (which is working on "Mathematical Superintelligence") just closed their $75 million Series A round led by Sequoia Capital https://harmonic.fun/news The New York Times did a p…
crossref
Steve Omohundro
2024-11-21T20:52:37Z
置信度 0.70
-
crossref
Euan Ritchie, Catherine Lovelock, Sarah Bekessy
2025-08-25T08:12:28Z
置信度 0.70
-
Coopetition alliances, where firms collaborate with their competitors, present a unique blend of cooperative and competitive pressures. Our study extends the understanding of coopetitor heterogeneity, particularly in technological and market overlaps, by shift…
crossref
Chiung-Yi Hwang
2024-07-09T19:00:23Z
置信度 0.70
-
Abstract In this paper, we conduct a preliminary study on the current development status in medical image alignment and build up a basic framework for image alignment. The feature space, search space, similarity measure, and search strategy of cardiac angiogra…
crossref
Ruili Wang, Baolong Zhang
2024-10-07T04:56:44Z
置信度 0.70
-
crossref
2024-07-08T06:48:47Z
置信度 0.70
-
crossref
Tao Lin, GanZhi Luo, WenYao Li, Wei Wang
2024-09-03T01:17:16Z
置信度 0.70
-
Aims Sagittal plane imbalance (SPI), or asymmetry between extension and flexion gaps, is an important issue in total knee arthroplasty (TKA). The purpose of this study was to compare SPI between kinematic alignment (KA), mechanical alignment (MA), and function…
crossref
Victor A. van de Graaf, Tony S. Shen, Jil A. Wood, Darren B. Chen 等
2024-08-19T03:10:27Z
置信度 0.70
-
crossref
2024-10-08T17:37:27Z
置信度 0.70
-
Abstract We present the 2024 edition of the ECN AI Baseline Index (EAII), an accessible benchmark evaluating large language models in competitive programming under contest conditions. The 2024 Sapientia–ECN universities division included 11 teams and 16 univer…
crossref
Zoltán Kátai, David Iclanzan
2026-04-13T01:37:45Z
置信度 0.70
-
crossref
2024-08-06T18:51:45Z
置信度 0.70
-
crossref
2024-10-11T20:24:33Z
置信度 0.70
-
Artificial intelligence (AI) has penetrated our daily lives so much that it is impossible to imagine life without AI. However, there has been a spate of accidents involving AI systems, leading to serious losses including loss of lives, financial fines, and los…
crossref
Srinivas Padmanabhuni, Neelima Vobugari
2024-07-01T13:29:01Z
置信度 0.70
-
This study investigates the AI assessment literacy of high school EFL teachers using the Chinese AI-powered chatbot, ERNIE Bot. Interviews and digital protocols revealed a dynamic relationship between teachers’ practical and conceptual knowledge, with both are…
crossref
Hao Xu
2024-10-04T17:13:41Z
置信度 0.70
-
crossref
Zachary Cooper
2024-09-18T06:40:51Z
置信度 0.70
-
crossref
2024-08-28T10:58:12Z
置信度 0.70
-
The topic for EAAI 2025's Mentored Undergraduate Research Challenge is PlayingWord Association Games. What does that mean? Where are the applications? How can you get started? We break down the topic, discuss applications, and explore project ideas in this col…
crossref
Richard G. Freedman
2024-05-03T22:08:02Z
置信度 0.70
-
crossref
Klaus Mainzer, Reinhard Kahle
2024-03-31T14:01:50Z
置信度 0.70
-
Based on my experience writing about and investing in Internet companies in the 1990s, I believe the evolution of generative AI will depend heavily on whether customers can find valuable ways to use the new technology. To that end, Chapter 3 answers questions …
crossref
Peter Cohan
2024-07-04T08:15:11Z
置信度 0.70
-
crossref
Jeffrey M. Feit
2024-05-15T10:00:18Z
置信度 0.70
-
How AI will challenge our ideas about personhood. Chatbots like ChatGPT have challenged human exceptionalism: we are no longer the only beings capable of generating language and ideas fluently. But is ChatGPT conscious? Or is it merely engaging in sophisticate…
crossref
James Boyle
2024-02-27T19:57:08Z
置信度 0.70
-
Will we allow generative artificial intelligence (AI) to define us, or will we use generative AI to define the next generation of legal practice? For better or for worse, many considered 2023 the year of AI. Launching in late 2022, ChatGPT set records for the …
crossref
Patrick Parsons
2024-05-09T15:53:35Z
置信度 0.70
-
One of the main challenges in high dimensional data analysis, networks, artificial intelligence, neuroscience, optimal transport and many other related areas of research is dealing with the exponential growth of the computational and sample complexity of sever…
crossref
2024-01-22T07:05:19Z
置信度 0.70
-
This chapter analyzes René Depestre’s 1950s writings through the lens of his alignment with global communism. Depestre’s Cold War trajectory was extraordinarily peripatetic: at turns benefitting from his communist ties and at other times suffering for them, De…
crossref
Christopher T. Bonner
2024-05-24T18:25:19Z
置信度 0.70
-
Continuous glucose monitoring has established that a molecular signal can be repeatedly measured in daily life and translated into clinically meaningful action. The next frontier is broader: wearable biosensors that monitor metabolites, electrolytes, hormones,…
europepmc
2026
置信度 0.80
-
Arc faults in low-voltage smart-farm distribution systems are difficult to detect reliably because normal current waveforms vary with load composition and operating conditions. This paper presents a progressive three-stage time-frequency learning framework tha…
europepmc
2026
置信度 0.80
-
Artificial intelligence is increasingly used in mental health nursing, yet its alignment with person-centred care remains underexplored. This scoping review examines the extent to which artificial intelligence applications in mental health nursing align with p…
europepmc
2026
置信度 0.80
-
We investigate the conversion of kinetic mixing dark photon dark matter into gravitational waves within the magnetic field of the Sun. Our study reveals that the WKB approximation is invalid in this scenario. We derive an analytic solution for the conversion p…
arxiv
Tengyu Ai, Yuxuan He, Jia Liu, Xiaolin Ma 等
2024-07-16T12:19:15Z
置信度 0.78
hep-ph
-
In each step of the creative writing process, writers must grapple with their creative goals and individual perspectives. This process affects the writer's sense of authenticity and their engagement with the written output. Fluent text generation by AIs risks …
arxiv
David Zhou, Sarah Sterman
2024-05-28T05:45:30Z
置信度 0.78
cs.HC
-
We describe observations and physical characteristics of Earth-crossing asteroid 2024 YR$_4$, discovered on 2024 December 27 by the Asteroid Terrestrial-impact Last Alert System. The asteroid has semi-major axis, $a$ = 2.52 au, eccentricity, $e$ = 0.66, inclin…
arxiv
Bryce T. Bolin, Josef Hanuš, Larry Denneau, Roberto Bonamico 等
2025-03-07T18:58:06Z
置信度 0.78
astro-ph.EP
-
The kernel thinning algorithm of Dwivedi & Mackey (2024) provides a better-than-i.i.d. compression of a generic set of points. By generating high-fidelity coresets of size significantly smaller than the input points, KT is known to speed up unsupervised ta…
arxiv
Albert Gong, Kyuseong Choi, Raaz Dwivedi
2024-10-17T16:48:51Z
置信度 0.78
cs.LGmath.STstat.ML
-
In an era marked by robust technological growth and swift information renewal, furnishing researchers and the populace with top-tier, avant-garde academic insights spanning various domains has become an urgent necessity. The KDD Cup 2024 AQA Challenge is geare…
arxiv
Wei Dai, Peng Fu, Chunjing Gan
2024-10-14T12:49:13Z
置信度 0.78
cs.IRcs.CLcs.LG
-
Clinical decision-making increasingly relies on timely and context-aware access to patient information within Electronic Health Records (EHRs), yet most existing natural language question-answering (QA) systems are evaluated solely on benchmark datasets, limit…
arxiv
Lingfei Qian, Mauro Giuffre, Yan Wang, Huan He 等
2026-01-15T03:02:15Z
置信度 0.78
cs.CL
-
As AI capabilities advance, we increasingly rely on powerful models to decompose complex tasks $\unicode{x2013}$ but what if the decomposer itself is malicious? Factored cognition protocols decompose complex tasks into simpler child tasks: one model creates th…
arxiv
Edward Lue Chee Lip, Anthony Channg, Diana Kim, Aaron Sandoval 等
2025-12-12T19:11:34Z
置信度 0.78
cs.CRcs.AI
-
Readers of applied-domain LLM capability evaluations want to know what AI systems can currently do. That literature answers a related, but consequentially different, question: what older, cheaper, less-elicited models could do months or years earlier (a 2026 p…
arxiv
David Gringras, Misha Salahshoor
2026-05-05T17:58:35Z
置信度 0.78
cs.CYcs.AIcs.CL
-
The significant progress in the development of Large Language Models has contributed to blurring the distinction between human and AI-generated text. The increasing pervasiveness of AI-generated text and the difficulty in detecting it poses new challenges for …
arxiv
Lucio La Cava, Davide Costa, Andrea Tagarelli
2024-07-12T15:44:56Z
置信度 0.78
cs.CLcs.AIcs.CYcs.HCphysics.soc-ph
-
How should we understand the social and political effects of the datafication of human life? This paper argues that the effects of data should be understood as a constitutive shift in social and political relations. We explore how datafication, or quantificati…
arxiv
Julian Posada, Nicholas Weller, Wendy H. Wong
2021-04-26T17:22:47Z
置信度 0.78
cs.CY
-
Popular and news media often portray teenagers with sensationalism, as both a risk to society and at risk from society. As AI begins to absorb some of the epistemic functions of traditional media, we study how teenagers in two countries speaking two languages:…
arxiv
Robert Wolfe, Aayushi Dangol, Bill Howe, Alexis Hiniker
2024-08-04T08:35:02Z
置信度 0.78
cs.CYcs.AIcs.CLcs.HCcs.LG
-
This paper presents our team's participation in the MEDIQA-ClinicalNLP2024 shared task B. We present a novel approach to diagnosing clinical dermatology cases by integrating large multimodal models, specifically leveraging the capabilities of GPT-4V under a re…
arxiv
Parth Vashisht, Abhilasha Lodha, Mukta Maddipatla, Zonghai Yao 等
2024-04-27T01:39:05Z
置信度 0.78
cs.AIcs.CL
-
Many works in the domain of artificial intelligence in games focus on board or video games due to the ease of reimplementing their mechanics. Decision-making problems in real-world sports share many similarities to such domains. Nevertheless, not many framewor…
arxiv
Carlo Nübel, Alexander Dockhorn, Sanaz Mostaghim
2024-08-12T07:22:46Z
置信度 0.78
cs.AI
-
ICEBERG is a liquid argon time projection chamber at Fermilab for the purpose of testing detector components and software for the Deep Underground Neutrino Experiment (DUNE). The detector features a 1.15m x 1m anode plane following the specifications of the DU…
arxiv
Alejandro Yankelevich
2025-01-24T02:32:10Z
置信度 0.78
physics.ins-dethep-ex
-
Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challenging. The root reason behind the misalignment has not been extensively investig…
arxiv
Dongzhi Jiang, Guanglu Song, Xiaoshi Wu, Renrui Zhang 等
2024-04-04T17:59:46Z
置信度 0.78
cs.CVcs.AIcs.CL
-
Recent progress in generative AI technology has made audio deepfakes remarkably more realistic. While current research on anti-spoofing systems primarily focuses on assessing whether a given audio sample is fake or genuine, there has been limited attention on …
arxiv
Nicholas Klein, Tianxiang Chen, Hemlata Tak, Ricardo Casal 等
2024-07-10T19:49:10Z
置信度 0.78
eess.AScs.SD
-
Visual-Language Alignment (VLA) has gained a lot of attention since CLIP's groundbreaking work. Although CLIP performs well, the typical direct latent feature alignment lacks clarity in its representation and similarity scores. On the other hand, lexical repre…
arxiv
Yifan Li, Yikai Wang, Yanwei Fu, Dongyu Ru 等
2024-07-25T07:35:27Z
置信度 0.78
cs.CVcs.AIcs.CLcs.LG
-
Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applications, such as autonomous vehicle control, facial recognition, and security cameras. Recent research has shown that acoustic vibration can induce …
arxiv
Nicole Villavicencio-Garduño, Maksim Ekin Eren, Milo Prisbrey, Ben Migliori 等
2026-06-12T17:22:53Z
置信度 0.78
cs.CVcs.AI
-
In this position paper, we discuss the potential for leveraging LLMs as interactive research tools to facilitate collaboration between human coders and AI to effectively annotate online risk data at scale. Collaborative human-AI labeling is a promising approac…
arxiv
Jinkyung Park, Pamela Wisniewski, Vivek Singh
2024-04-11T17:20:57Z
置信度 0.78
cs.HCcs.AI
-
Dementia and especially Alzheimer's disease (AD) are the most common causes of cognitive decline in elderly people. A spread of the above mentioned mental health problems in aging societies is causing a significant medical and economic burden in many countries…
arxiv
Tomasz M. Rutkowski, Qibin Zhao, Masao S. Abe, Mihoko Otake
2018-11-30T06:58:16Z
置信度 0.78
q-bio.NCcs.AIcs.LG
-
Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable performance. In this paper, our key insight is that modern Large Language Models…
arxiv
Junxi Wu, Kailin Huang, Dongjian Hu, Bin Chen 等
2026-04-18T09:12:24Z
置信度 0.78
cs.AI
-
We reconstruct the cosmological background evolution under the scenario of dynamical dark energy through the Gaussian process approach, using the latest Dark Energy Spectroscopic Instrument (DESI) baryon acoustic oscillations (BAO) combined with other observat…
arxiv
Yuhang Yang, Xin Ren, Qingqing Wang, Zhiyu Lu 等
2024-04-30T10:35:04Z
置信度 0.78
astro-ph.COgr-qchep-phhep-th
-
In this report, we summarize the integrated multilingual audio processing pipeline developed by our team for the inaugural NCIIPC Startup India AI GRAND CHALLENGE, addressing Problem Statement 06: Language-Agnostic Speaker Identification and Diarisation, and s…
arxiv
Nikhil Raghav, Arnab Banerjee, Janojit Chakraborty, Avisek Gupta 等
2025-12-11T11:49:27Z
置信度 0.78
cs.SD
-
The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboratio…
arxiv
LSST Dark Energy Science Collaboration, Eric Aubourg, Camille Avestruz, Matthew R. Becker 等
2026-01-20T18:46:42Z
置信度 0.78
astro-ph.IMastro-ph.COcs.AIcs.LGstat.ML
-
Legal case documents play a critical role in judicial proceedings. As the number of cases continues to rise, the reliance on manual drafting of legal case documents is facing increasing pressure and challenges. The development of large language models (LLMs) o…
arxiv
Haitao Li, Jiaying Ye, Yiran Hu, Jia Chen 等
2025-02-25T08:03:32Z
置信度 0.78
cs.CL
-
This paper introduces a novel generalized self-imitation learning ($\textbf{GSIL}$) framework, which effectively and efficiently aligns large language models with offline demonstration data. We develop $\textbf{GSIL}$ by deriving a surrogate objective of imita…
arxiv
Teng Xiao, Mingxiao Li, Yige Yuan, Huaisheng Zhu 等
2024-10-14T02:21:29Z
置信度 0.78
cs.CLcs.LG
-
With the rapid development and application of foundation models (FMs), it is foreseeable that FMs will play an important role in future wireless communications. As current Artificial Intelligence (AI) algorithms applied in wireless networks are dedicated model…
arxiv
Wen Tong, Chenghui Peng, Tingting Yang, Fei Wang 等
2023-11-22T02:15:16Z
置信度 0.78
cs.NI
-
As Artificial Intelligence (AI) continues to advance rapidly, Friendly AI (FAI) has been proposed to advocate for more equitable and fair development of AI. Despite its importance, there is a lack of comprehensive reviews examining FAI from an ethical perspect…
arxiv
Qiyang Sun, Yupei Li, Emran Alturki, Sunil Munthumoduku Krishna Murthy 等
2024-12-19T17:56:08Z
置信度 0.78
cs.AIcs.CY
-
The integration of large language models (LLMs) into education presents unprecedented opportunities for scalable personalized learning. However, standard LLMs often function as generic information providers, lacking alignment with fundamental pedagogical princ…
arxiv
Siyu Song, Wentao Liu, Ye Lu, Ruohua Zhang 等
2025-07-27T15:56:29Z
置信度 0.78
cs.LGcs.AI
-
Smart home systems are gaining popularity as homeowners strive to enhance their living and working environments while minimizing energy consumption. However, the adoption of artificial intelligence (AI)-enabled decision-making models in smart home systems face…
arxiv
Md Shajalal, Alexander Boden, Gunnar Stevens, Delong Du 等
2024-04-23T22:31:42Z
置信度 0.78
cs.HCcs.AI
-
Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize to novel (i…
arxiv
Ayan Chatterjee, Robin Walters, Zohair Shafi, Omair Shafi Ahmed 等
2021-12-25T01:52:58Z
置信度 0.78
q-bio.QMcs.LG
-
Traditional defect classification approaches are facing with two barriers. (1) Insufficient training data and unstable data quality. Collecting sufficient defective sample is expensive and time-costing, consequently leading to dataset variance. It introduces t…
arxiv
Chih-Chung Hsu, Chia-Ming Lee, Chun-Hung Sun, Kuang-Ming Wu
2024-04-08T04:17:27Z
置信度 0.78
cs.CVcs.LG
-
Driving the Digital Omnibus on AI are growing concerns within the European Union about economic growth, competitiveness, innovation and regulatory simplification. What is particularly striking about the Digital Omnibus on AI is that it seeks to amend the AI Ac…
arxiv
Donal Casey, Liane Colonna
2026-06-14T07:59:15Z
置信度 0.78
cs.CY
-
Unlike classical control theory, such as Linear Quadratic Control (LQC), real-world control problems are highly complex. These problems often involve adversarial perturbations, bandit feedback models, and non-quadratic, adversarially chosen cost functions. A f…
arxiv
Y. Jennifer Sun, Zhou Lu
2024-10-01T18:35:08Z
置信度 0.78
cs.LGmath.OC
-
This paper aims to explore two competing data science methodologies to attempt answering the question, "Which issues contributed most to voters' choice in the 2024 presidential election?" The methodologies involve novel empirical evidence driven by artificial …
arxiv
Raisa M. Simoes, Timoteo Kelly, Eduardo J. Simoes, Praveen Rao
2025-10-09T06:02:10Z
置信度 0.78
cs.SIcs.CL
-
During its annual conference in 2024, the French Society of Astronomy & Astrophysics (SF2A) hosted a special session dedicated to discussing the environmental transition within the scope of our occupation. Since 2021, thinking on this subject has progresse…
arxiv
Faustine Cantalloube, Camille Noûs
2024-12-13T09:24:42Z
置信度 0.78
astro-ph.IMastro-ph.EP
-
In-context learning (ICL) allows LLMs to learn from examples without changing their weights: this is a particularly promising capability for long-context LLMs that can potentially learn from many examples. Recently, Lin et al. (2024) proposed URIAL, a method u…
arxiv
Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
2024-05-30T09:28:56Z
置信度 0.78
cs.CLcs.AIcs.LG
-
Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses due to minor changes…
arxiv
Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing 等
2024-03-21T08:21:12Z
置信度 0.78
cs.CL
-
Artificial Intelligence (AI) systems are frequently employed in online services to provide personalized experiences to users based on large collections of data. However, AI systems can be designed in different ways, with black-box AI systems appearing as compl…
arxiv
Julian Rosenberger, Sophie Kuhlemann, Verena Tiefenbeck, Mathias Kraus 等
2025-02-27T16:28:09Z
置信度 0.78
cs.LGcs.HC