AI 安全与对齐 · 全部实体（第 64 / 100 页）

本页收录第 6301–6400 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025
  The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate multiple tasks to different agents, and even write a full piece of software purely out of natural language. In reality,…
  arxiv Ruanqianqian Huang, Avery Reyna, Sorin Lerner, Haijun Xia 等 2025-12-16T02:15:06Z 置信度 0.78 cs.SEcs.AIcs.HC
• Enabling Responsible, Secure and Sustainable Healthcare AI - A Strategic Framework for Clinical and Operational Impact
  We offer a pragmatic model to operationalize responsible, secure, and sustainable healthcare AI, aligning world-class technical excellence with organizational readiness. The framework includes five key pillars - Leadership & Strategy, MLOps & Technical…
  arxiv Jimmy Joseph 2025-10-09T12:40:59Z 置信度 0.78 cs.CY
• Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback
  Large language models (LLMs) have demonstrated remarkable capabilities across various research domains, including the field of Information Retrieval (IR). However, the responses generated by off-the-shelf LLMs tend to be generic, i.e., cannot capture the disti…
  arxiv Qian Dong, Yiding Liu, Qingyao Ai, Zhijing Wu 等 2023-09-29T09:14:53Z 置信度 0.78 cs.IR
• GATEBLEED: Exploiting On-Core Accelerator Power Gating for High Performance & Stealthy Attacks on AI
  As power consumption from AI training and inference continues to increase, AI accelerators are being integrated directly into the CPU. Intel's Advanced Matrix Extensions (AMX) is one such example, debuting on the 4th generation Intel Xeon Scalable CPU. We disc…
  arxiv Joshua Kalyanapu, Farshad Dizani, Darsh Asher, Azam Ghanbari 等 2025-07-22T21:41:43Z 置信度 0.78 cs.CR
• IConMark: Robust Interpretable Concept-Based Watermark For AI Images
  With the rapid rise of generative AI and synthetic media, distinguishing AI-generated images from real ones has become crucial in safeguarding against misinformation and ensuring digital authenticity. Traditional watermarking techniques have shown vulnerabilit…
  arxiv Vinu Sankar Sadasivan, Mehrdad Saberi, Soheil Feizi 2025-07-17T05:38:30Z 置信度 0.78 cs.CVcs.AIcs.CR
• Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
  State-of-the-art neural network (NN) verifiers demonstrate that applying the branch-and-bound (BaB) procedure with fast bounding techniques plays a key role in tackling many challenging verification properties. In this work, we introduce the linear constraint-…
  arxiv Duo Zhou, Jorge Chavez, Hesun Chen, Grani A. Hanasusanto 等 2025-12-11T19:59:37Z 置信度 0.78 cs.LGcs.AIcs.CRmath.OC
• SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation
  Vision-language temporal alignment is a crucial capability for human dynamic recognition and cognition in real-world scenarios. While existing research focuses on capturing vision-language relevance, it faces limitations due to biased temporal distributions, i…
  arxiv Hao Du, Bo Wu, Yan Lu, Zhendong Mao 2025-04-08T11:31:37Z 置信度 0.78 cs.CV
• Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases
  Recent failures such as Google Gemini generating people of color in Nazi-era uniforms illustrate how AI outputs can be factually plausible yet socially harmful. AI models are increasingly evaluated for "fairness," yet existing benchmarks often conflate two fun…
  arxiv Jen-tse Huang, Yuhang Yan, Linqi Liu, Yixin Wan 等 2025-02-09T10:54:11Z 置信度 0.78 cs.CL
• The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence
  An AI audit record is useful only if its durability and trust boundary are explicit. Returning a guarded decision before any durable write minimizes latency, but it cannot guarantee that evidence survives an immediate crash. We rebuild RuntimeGuard-AI around t…
  arxiv Neeraj Kumar Singh Beshane 2026-08-17T22:35:07Z 置信度 0.78 cs.CRcs.AI
• Cyber security of Mega Events: A Case Study of Securing the Digital Infrastructure for MahaKumbh 2025 -- A 45 days Mega Event of 600 Million Footfalls
  Mega events such as the Olympics, World Cup tournaments, G-20 Summit, religious events such as MahaKumbh are increasingly digitalized. From event ticketing, vendor booth or lodging reservations, sanitation, event scheduling, customer service, crime reporting, …
  arxiv Rohit Negi, Amit Negi, Manish Sharma, S. Venkatesan 等 2025-07-21T14:21:59Z 置信度 0.78 cs.CRcs.CY
• Biospheric AI
  The dominant paradigm in AI ethics and value alignment is highly anthropocentric. The focus of these disciplines is strictly on human values which limits the depth and breadth of their insights. Recently, attempts to expand to a sentientist perspective have be…
  arxiv Marcin Korecki 2024-01-31T13:04:34Z 置信度 0.78 cs.CYcs.AI
• Not someone, but something: Rethinking trust in the age of medical AI
  As artificial intelligence (AI) becomes embedded in healthcare, trust in medical decision-making is changing fast. Nowhere is this shift more visible than in radiology, where AI tools are increasingly embedded across the imaging workflow - from scheduling and …
  arxiv Jan Beger 2025-04-04T14:09:20Z 置信度 0.78 cs.CYcs.AIcs.HC
• Human-Aligned Image Models Improve Visual Decoding from the Brain
  Decoding visual images from brain activity has significant potential for advancing brain-computer interaction and enhancing the understanding of human perception. Recent approaches align the representation spaces of images and brain activity to enable visual d…
  arxiv Nona Rajabi, Antônio H. Ribeiro, Miguel Vasco, Farzaneh Taleb 等 2025-02-05T11:14:51Z 置信度 0.78 cs.CVcs.LG
• Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
  The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, such as a planning agent for subgoal generation and a grounding agent for executin…
  arxiv Minghang Zhu, Zhengliang Shi, Zhiwei Xu, Shiguang Wu 等 2025-09-11T17:15:45Z 置信度 0.78 cs.CL
• Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning
  Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos partially relevant to a given query. The core challenge lies in learning robust query-video alignment against spurious semantic correlations arising from inherent data uncertainty: 1) …
  arxiv Long Zhang, Peipei Song, Jianfeng Dong, Kun Li 等 2025-09-01T11:30:43Z 置信度 0.78 cs.CVcs.MM
• Emergency Response Measures for Catastrophic AI Risk
  Chinese authorities are extending the country's four-phase emergency response framework (prevent, warn, respond, and recover) to address risks from advanced artificial intelligence (AI). Concrete mechanisms for the proactive prevention and warning phases, howe…
  arxiv James Zhang, Miles Kodama, Zongze Wu, Michael Chen 等 2025-10-28T22:07:58Z 置信度 0.78 cs.CY
• HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
  This paper introduces HarmonySet, a comprehensive dataset designed to advance video-music understanding. HarmonySet consists of 48,328 diverse video-music pairs, annotated with detailed information on rhythmic synchronization, emotional alignment, thematic coh…
  arxiv Zitang Zhou, Ke Mei, Yu Lu, Tianyi Wang 等 2025-03-03T16:42:46Z 置信度 0.78 cs.CV
• Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
  Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data. However, previous GCD methods face challenges due to inconsistent optimization objectives and category confusion…
  arxiv Jizhou Han, Shaokun Wang, Yuhang He, Chenhao Ding 等 2025-07-07T07:34:41Z 置信度 0.78 cs.CV
• Labeling Synthetic Content: User Perceptions of Warning Label Designs for AI-generated Content on Social Media
  In this research, we explored the efficacy of various warning label designs for AI-generated content on social media platforms e.g., deepfakes. We devised and assessed ten distinct label design samples that varied across the dimensions of sentiment, color/icon…
  arxiv Dilrukshi Gamage, Dilki Sewwandi, Min Zhang, Arosha Bandara 2025-02-14T10:35:42Z 置信度 0.78 cs.HCcs.AIcs.CYcs.ET
• Can LLMs Talk 'Sex'? Exploring How AI Models Handle Intimate Conversations
  This study examines how four prominent large language models (Claude 3.7 Sonnet, GPT-4o, Gemini 2.5 Flash, and Deepseek-V3) handle sexually oriented requests through qualitative content analysis. By evaluating responses to prompts ranging from explicitly sexua…
  arxiv Huiqian Lai 2025-06-05T18:55:37Z 置信度 0.78 cs.CYcs.IT
• AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment
  Multimodal Large Language Models (MLLMs) are increasingly applied in Personalized Image Aesthetic Assessment (PIAA) as a scalable alternative to expert evaluations. However, their predictions may reflect subtle biases influenced by demographic factors such as …
  arxiv Kun Li, Lai-Man Po, Hongzheng Yang, Xuyuan Xu 等 2025-09-15T06:25:39Z 置信度 0.78 cs.CLcs.CY
• Making Effective Decisions: Machine Learning and the Ecogame in 1970
  This paper considers Ecogame, an innovative art project of 1970, whose creators believed in a positive vision of a technological future; an understanding, posited on cybernetics, of a future that could be participatory via digital means, and therefore more dem…
  arxiv Catherine Mason 2025-08-09T15:51:26Z 置信度 0.78 cs.CYcs.AI
• MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting
  Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks. However, existing inpainting methods often suffer from problems such as semantic misalignment, s…
  arxiv Jun Huang, Ting Liu, Yihang Wu, Xiaochao Qu 等 2025-06-30T03:06:54Z 置信度 0.78 cs.CV
• CAMILA: Context-Aware Masking for Image Editing with Language Alignment
  Text-guided image editing has been allowing users to transform and synthesize images through natural language instructions, offering considerable flexibility. However, most existing image editing models naively attempt to follow all user instructions, even if …
  arxiv Hyunseung Kim, Chiho Choi, Srikanth Malla, Sai Prahladh Padmanabhan 等 2025-09-24T03:20:44Z 置信度 0.78 cs.CV
• Zer0n: An AI-Assisted Vulnerability Discovery and Blockchain-Backed Integrity Framework
  As vulnerability research increasingly adopts generative AI, a critical reliance on opaque model outputs has emerged, creating a "trust gap" in security automation. We address this by introducing Zer0n, a framework that anchors the reasoning capabilities of La…
  arxiv Harshil Parmar, Pushti Vyas, Prayers Khristi, Priyank Panchal 2026-01-11T18:27:52Z 置信度 0.78 cs.CRcs.AIcs.SE
• Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
  Document Image Machine Translation (DIMT) aims to translate text within document images, facing generalization challenges due to limited training data and the complex interplay between visual and textual information. To address these challenges, we introduce M…
  arxiv Yupu Liang, Yaping Zhang, Zhiyang Zhang, Yang Zhao 等 2025-07-10T09:18:06Z 置信度 0.78 cs.CLcs.AIcs.CV
• First African Digital Humanism Summer School 2025
  Artificial intelligence (AI) has become a transformative force across global societies, reshaping the ways we communicate, collaborate, and make decisions. Yet, as AI systems increasingly mediate interactions between humans, questions about the ability to take…
  arxiv Carine P. Mukamakuza, Monika Lanzenberger, George Metakides, Tim Brown 等 2026-01-11T20:55:37Z 置信度 0.78 cs.CYcs.AI
• From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge
  This report presents SceneNet and KnowledgeNet, our approaches developed for the HD-EPIC VQA Challenge 2025. SceneNet leverages scene graphs generated with a multi-modal large language model (MLLM) to capture fine-grained object interactions, spatial relations…
  arxiv Agnese Taluzzi, Davide Gesualdi, Riccardo Santambrogio, Chiara Plizzari 等 2025-06-10T08:21:38Z 置信度 0.78 cs.CV
• keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection
  Identification of hallucination spans in black-box language model generated text is essential for applications in the real world. A recent attempt at this direction is SemEval-2025 Task 3, Mu-SHROOM-a Multilingual Shared Task on Hallucinations and Related Obse…
  arxiv Saketh Reddy Vemula, Parameswari Krishnamurthy 2025-05-23T05:25:14Z 置信度 0.78 cs.CLcs.AI
• AI Adoption in S&P 500 Firms
  The adoption of artificial intelligence (AI) by large enterprises is an important potential source of aggregate productivity improvement and labor market impact. We study AI adoption of S&P 500 firms over the period 2016 to 2025, estimating adoption at the…
  arxiv Yang Yu, Martin Fleming, Lucy Hampton, Christophe Combemale 等 2026-07-09T20:26:22Z 置信度 0.78 econ.GN
• Which Contributions Deserve Credit? Perceptions of Attribution in Human-AI Co-Creation
  AI systems powered by large language models can act as capable assistants for writing and editing. In these tasks, the AI system acts as a co-creative partner, making novel contributions to an artifact-under-creation alongside its human partner(s). One questio…
  arxiv Jessica He, Stephanie Houde, Justin D. Weisz 2025-02-25T16:48:10Z 置信度 0.78 cs.HCcs.AIcs.CY
• Evaluating AI Providers' Frontier Safety Frameworks
  Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats these Frameworks as ext…
  arxiv Lily Stelling, Malcolm Murray, Bruno Galizzi, Max Schaffelder 等 2025-12-01T00:55:18Z 置信度 0.78 cs.CY
• How We Won BraTS-SSA 2025: Brain Tumor Segmentation in the Sub-Saharan African Population Using Segmentation-Aware Data Augmentation and Model Ensembling
  Brain tumors, particularly gliomas, pose significant chall-enges due to their complex growth patterns, infiltrative nature, and the variability in brain structure across individuals, which makes accurate diagnosis and monitoring difficult. Deep learning models…
  arxiv Claudia Takyi Ankomah, Livingstone Eli Ayivor, Ireneaus Nyame, Leslie Wambo 等 2025-10-03T23:32:35Z 置信度 0.78 eess.IVcs.CV
• ChatBench: From Static Benchmarks to Human-AI Evaluation
  With the rapid adoption of LLM-based chatbots, there is a pressing need to evaluate what humans and LLMs can achieve together. However, standard benchmarks, such as MMLU, measure LLM capabilities in isolation (i.e., "AI-alone"). Here, we design and conduct a u…
  arxiv Serina Chang, Ashton Anderson, Jake M. Hofman 2025-03-22T01:21:40Z 置信度 0.78 cs.CLcs.AIcs.CYcs.HC
• Left shifting analysis of Human-Autonomous Team interactions to analyse risks of autonomy in high-stakes AI systems
  Developing high-stakes autonomous systems that include Artificial Intelligence (AI) components is complex; the consequences of errors can be catastrophic, yet it is challenging to plan for all operational cases. In stressful scenarios for the human operator, s…
  arxiv Ben Larwood, Oliver J. Sutton, Callum Cockburn 2025-12-03T07:21:55Z 置信度 0.78 cs.HCeess.SY
• KMT-2025-BLG-0975Lb and KMT-2025-BLG-1160Lb: Two Uranus-Mass Planets Beyond the Snow Line Discovered by Microlensing
  We present the analysis of two planetary microlensing events, KMT-2025-BLG-0975 and KMT-2025-BLG-1160, discovered during the 2025 Galactic bulge microlensing season through high-cadence survey observations. In both events, short-duration anomalies near the pea…
  arxiv Cheongho Han, Chung-Uk Lee, Andrzej Udalski, Andrew Gould 等 2026-07-28T04:01:13Z 置信度 0.78 astro-ph.EPastro-ph.GA
• Enhancing Critical Thinking in Generative AI Search with Metacognitive Prompts
  The growing use of Generative AI (GenAI) conversational search tools has raised concerns about their effects on people's metacognitive engagement, critical thinking, and learning. As people increasingly rely on GenAI to perform tasks such as analyzing and appl…
  arxiv Anjali Singh, Zhitong Guan, Soo Young Rieh 2025-05-29T21:32:46Z 置信度 0.78 cs.HC
• TRepLiNa: Layer-wise CKA+REPINA Alignment Improves Low-Resource Machine Translation in Aya-23 8B
  The 2025 Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo) Language Challenge addresses one of India's most pressing linguistic gaps: the lack of resources for its diverse low-resource languages (LRLs). In this study, we investigate whethe…
  arxiv Toshiki Nakai, Ravi Kiran Chikkala, Lena Sophie Oberkircher, Nicholas Jennings 等 2025-10-03T17:36:12Z 置信度 0.78 cs.CLcs.AI
• More-than-Human Storytelling: Designing Longitudinal Narrative Engagements with Generative AI
  Longitudinal engagement with generative AI (GenAI) storytelling agents is a timely but less charted domain. We explored multi-generational experiences with "Dreamsmithy," a daily dream-crafting app, where participants (N = 28) co-created stories with AI narrat…
  arxiv Émilie Fabre, Katie Seaborn, Shuta Koiwai, Mizuki Watanabe 等 2025-05-20T06:10:29Z 置信度 0.78 cs.HCcs.AIcs.CYcs.SDeess.AS
• ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
  Backpropagation-based approaches aim to align diffusion models with reward functions through end-to-end backpropagation of the reward gradient within the denoising chain, offering a promising perspective. However, due to the computational costs and the risk of…
  arxiv Xiefan Guo, Miaomiao Cui, Liefeng Bo, Di Huang 2025-07-30T12:19:01Z 置信度 0.78 cs.CV
• Revisiting CLIP: Efficient Alignment of 3D MRI and Tabular Data using Domain-Specific Foundation Models
  Multi-modal models require aligned, shared embedding spaces. However, common CLIP-based approaches need large amounts of samples and do not natively support 3D or tabular data, both of which are crucial in the medical domain. To address these issues, we revisi…
  arxiv Jakob Krogh Petersen, Valdemar Licht, Mads Nielsen, Asbjørn Munk 2025-01-23T19:34:48Z 置信度 0.78 cs.CVcs.AIcs.LG
• Recommendation systems in e-commerce applications with machine learning methods
  E-commerce platforms are increasingly reliant on recommendation systems to enhance user experience, retain customers, and, in most cases, drive sales. The integration of machine learning methods into these systems has significantly improved their efficiency, p…
  arxiv Aneta Poniszewska-Maranda, Magdalena Pakula, Bozena Borowska 2025-06-15T10:51:01Z 置信度 0.78 cs.IRcs.LG
• A Neuro-AI Interface for Evaluating Generative Adversarial Networks
  Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. However, evaluating the performance of GANs is still an open and challenging problem. Existi…
  arxiv Zhengwei Wang, Qi She, Alan F. Smeaton, Tomas E. Ward 等 2020-03-05T17:53:43Z 置信度 0.78 cs.CVcs.HCcs.LGeess.IV
• Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
  We introduce SAFEMax, a novel method for Machine Unlearning in diffusion models. Grounded in information-theoretic principles, SAFEMax maximizes the entropy in generated images, causing the model to generate Gaussian noise when conditioned on impermissible cla…
  arxiv Christoforos N. Spartalis, Theodoros Semertzidis, Petros Daras, Efstratios Gavves 2025-08-28T13:29:21Z 置信度 0.78 cs.LGcs.AIcs.CV
• Appeal and Scope of Misinformation Spread by AI Agents and Humans
  This work examines the influence of misinformation and the role of AI agents, called bots, on social network platforms. To quantify the impact of misinformation, it proposes two new metrics based on attributes of tweet engagement and user network position: App…
  arxiv Lynnette Hui Xian Ng, Wenqi Zhou, Kathleen M. Carley 2025-05-07T00:07:04Z 置信度 0.78 cs.SIphysics.soc-ph
• Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge
  The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy with constraints such as latency, memory capacity, and energy use. The 2025 challenge featured three tracks: (1…
  arxiv Zihao Ye, Yung-Hsiang Lu, Xiao Hu, Shuai Zhang 等 2026-04-21T04:00:55Z 置信度 0.78 cs.CV
• Moving Matter: Using a Single, Simple Robot to Reconfigure a Connected Set of Building Blocks
  We implement and evaluate different methods for the reconfiguration of a connected arrangement of tiles into a desired target shape, using a single active robot that can move along the tile structure. This robot can pick up, carry, or drop off one tile at a ti…
  arxiv Javier Garcia, Jonas Friemel, Ramin Kosfeld, Michael Yannuzzi 等 2025-06-29T17:03:44Z 置信度 0.78 cs.ROcs.CGcs.DS
• An Investigation of the Impact of COVID-19 Non-Pharmaceutical Interventions and Economic Support Policies on Foreign Exchange Markets with Explainable AI Techniques
  Since the onset of the the COVID-19 pandemic, many countries across the world have implemented various non-pharmaceutical interventions (NPIs) to contain the spread of virus, as well as economic support policies (ESPs) to save their economies. The pandemic and…
  arxiv Siyuan Liu, Mehmet Orcun Yalcin, Hsuan Fu, Xiuyi Fan 2021-11-02T07:02:28Z 置信度 0.78 econ.GNcs.CY
• Structured dataset of reported cloud seeding activities in the United States (2000-2025) using an LLM
  Cloud seeding, a weather modification technique used to increase precipitation, has been practiced in the western United States since the 1940s. However, comprehensive datasets are not currently available to analyze these efforts. To address this gap, we prese…
  arxiv Jared Joseph Donohue, Kara D. Lamb 2025-05-02T19:47:30Z 置信度 0.78 physics.ao-ph
• Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization
  To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous methods (such as quantizat…
  arxiv Yangcheng Gao, Zhao Zhang, Richang Hong, Haijun Zhang 等 2022-04-30T06:58:56Z 置信度 0.78 cs.CV
• Will AI Make Cyber Swords or Shields: A few mathematical models of technological progress
  We aim to demonstrate the value of mathematical models for policy debates about technological progress in cybersecurity by considering phishing, vulnerability discovery, and the dynamics between patching and exploitation. We then adjust the inputs to those mat…
  arxiv Andrew J Lohn, Krystal Alex Jackson 2022-07-27T23:27:21Z 置信度 0.78 cs.CRcs.AIcs.CY
• Addressing Data Imbalance in Transformer-Based Multi-Label Emotion Detection with Weighted Loss
  This paper explores the application of a simple weighted loss function to Transformer-based models for multi-label emotion detection in SemEval-2025 Shared Task 11. Our approach addresses data imbalance by dynamically adjusting class weights, thereby enhancing…
  arxiv Xia Cui 2025-07-15T14:53:33Z 置信度 0.78 cs.CL
• Open-Set Cross-Network Node Classification via Unknown-Excluded Adversarial Graph Domain Alignment
  Existing cross-network node classification methods are mainly proposed for closed-set setting, where the source network and the target network share exactly the same label space. Such a setting is restricted in real-world applications, since the target network…
  arxiv Xiao Shen, Zhihao Chen, Shirui Pan, Shuang Zhou 等 2025-02-16T03:00:42Z 置信度 0.78 cs.SI
• VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment
  3D Gaussian Splatting has recently emerged as an efficient solution for high-quality and real-time novel view synthesis. However, its capability for accurate surface reconstruction remains underexplored. Due to the discrete and unstructured nature of Gaussians…
  arxiv Qing Li, Huifang Feng, Xun Gong, Yu-Shen Liu 2025-10-13T14:44:50Z 置信度 0.78 cs.CV
• Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization
  Imagine hearing a dog bark and turning toward the sound only to see a parked car, while the real, silent dog sits elsewhere. Such sensory conflicts test perception, yet humans reliably resolve them by prioritizing sound over misleading visuals. Despite advance…
  arxiv Yanhao Jia, Ji Xie, S Jivaganesh, Hao Li 等 2025-05-16T13:13:25Z 置信度 0.78 cs.SDcs.AIcs.CVcs.MMeess.AS
• On-Device Watermarking: A Socio-Technical Imperative For Authenticity In The Age of Generative AI
  As generative AI models produce increasingly realistic output, both academia and industry are focusing on the ability to detect whether an output was generated by an AI model or not. Many of the research efforts and policy discourse are centered around robust …
  arxiv Houssam Kherraz 2025-04-15T20:36:52Z 置信度 0.78 cs.CRcs.AI
• Personality-Enhanced Multimodal Depression Detection in the Elderly
  This paper presents our solution to the Multimodal Personality-aware Depression Detection (MPDD) challenge at ACM MM 2025. We propose a multimodal depression detection model in the Elderly that incorporates personality characteristics. We introduce a multi-fea…
  arxiv Honghong Wang, Jing Deng, Rong Zheng 2025-10-09T09:41:51Z 置信度 0.78 cs.SDcs.MMeess.AS
• NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild
  This paper presents an overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, held in conjunction with the NTIRE workshop at CVPR 2026. The goal of this challenge was to develop detection models capable of distinguishing real …
  arxiv Aleksandr Gushchin, Khaled Abud, Ekaterina Shumitskaya, Artem Filippov 等 2026-04-13T13:53:11Z 置信度 0.78 cs.CV
• ECFA Higgs, electroweak, and top Factory Study
  The ECFA Higgs, electroweak, and top Factory Study ran between 2021 and 2025 as a broad effort across the experimental and theoretical particle physics communities, bringing together participants from many different proposed future collider projects. Activitie…
  arxiv H. Abidi, J. A. Aguilar-Saavedra, S. Airen, S. Ajmal 等 2025-06-18T12:05:45Z 置信度 0.78 hep-exhep-ph
• Composition and Alignment of Diffusion Models using Constrained Learning
  Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions. To improve the quality of generated samples and their compliance with user requirements, two commonly used methods are: (i) Alignment, whic…
  arxiv Shervin Khalafi, Ignacio Hounie, Dongsheng Ding, Alejandro Ribeiro 2025-08-26T15:06:30Z 置信度 0.78 cs.LGeess.IVstat.ML
• DynaWeb: Model-Based Reinforcement Learning of Web Agents
  The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by the challenges of int…
  arxiv Hang Ding, Peidong Liu, Junqiao Wang, Ziwei Ji 等 2026-01-29T18:59:07Z 置信度 0.78 cs.CLcs.AI
• Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective
  Cross-lingual Named Entity Recognition (CL-NER) aims to transfer knowledge from high-resource languages to low-resource languages. However, existing zero-shot CL-NER (ZCL-NER) approaches primarily focus on Latin script language (LSL), where shared linguistic f…
  arxiv Zhihao Zhang, Sophia Yat Mei Lee, Dong Zhang, Shoushan Li 等 2025-09-01T05:49:49Z 置信度 0.78 cs.CL
• Exploring the Collaborative Co-Creation Process with AI: A Case Study in Novice Music Production
  Artificial intelligence is reshaping creative domains, yet its co-creative processes, especially in group settings with novice users, remain under explored. To bridge this gap, we conducted a case study in a college-level course where nine undergraduate studen…
  arxiv Yue Fu, Michele Newman, Lewis Going, Qiuzi Feng 等 2025-01-25T17:00:17Z 置信度 0.78 cs.HCcs.AI
• Cross-modal Full-mode Fine-grained Alignment for Text-to-Image Person Retrieval
  Text-to-Image Person Retrieval (TIPR) is a cross-modal matching task designed to identify the person images that best correspond to a given textual description. The key difficulty in TIPR is to realize robust correspondence between the textual and visual modal…
  arxiv Hao Yin, Xin Man, Feiyu Chen, Jie Shao 等 2025-09-17T07:12:05Z 置信度 0.78 cs.CV
• Baryon Number Violation: From Nuclear Matrix Elements to BSM Physics
  Processes that violate baryon number, most notably proton decay and $n\bar n$ transitions, are promising probes of physics beyond the Standard Model (BSM) needed to understand the lack of antimatter in the Universe. To interpret current and forthcoming experim…
  arxiv Leah J. Broussard, Andreas Crivellin, Martin Hoferichter, Sergey Syritsyn 等 2025-04-23T18:00:00Z 置信度 0.78 hep-phhep-exhep-latnucl-exnucl-th
• Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
  Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight decoder-based architect…
  arxiv Bianca-Mihaela Ganescu, Suchir Salhan, Andrew Caines, Paula Buttery 2025-10-09T17:10:36Z 置信度 0.78 cs.AIcs.CLcs.LG
• On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices
  AI code generation tools have gained significant popularity among developers, who use them to assist in software development due to their capability to generate code. Existing studies mainly explored the quality, e.g., correctness and security, of AI-generated…
  arxiv Syed Mohammad Kashif, Peng Liang, Amjed Tahir 2025-04-23T07:52:39Z 置信度 0.78 cs.SEcs.AI
• Mindsets and Management: AI and Gender (In)Equitable Access to Finance
  A growing trend in financial technology (fintech) is the use of mobile phone data and machine learning (ML) to provide credit scores- and subsequently, opportunities to access loans- to groups left out of traditional banking. This paper draws on interview data…
  arxiv Genevieve Smith 2025-04-09T22:28:21Z 置信度 0.78 cs.CY
• Model Cards Revisited: Bridging the Gap Between Theory and Practice for Ethical AI Requirements
  Model cards are the primary documentation framework for developers of artificial intelligence (AI) models to communicate critical information to their users. Those users are often developers themselves looking for relevant documentation to ensure that their AI…
  arxiv Tim Puhlfürß, Julia Butzke, Walid Maalej 2025-07-08T14:19:50Z 置信度 0.78 cs.SE
• Optimistic MEV in Ethereum Layer 2s: Why Blockspace Is Always in Demand
  Layer 2 rollups are rapidly absorbing DeFi activity, securing over $40 billion and accounting for nearly half of Ethereum's DEX volume by Q1 2025, yet their MEV dynamics remain understudied. We address this gap by defining and quantifying optimistic MEV, a for…
  arxiv Ozan Solmaz, Lioba Heimbach, Yann Vonlanthen, Roger Wattenhofer 2025-06-17T17:58:28Z 置信度 0.78 cs.CE
• SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
  Existing preference optimization objectives for language model alignment require additional hyperparameters that must be extensively tuned to achieve optimal performance, increasing both the complexity and time required for fine-tuning large language models. I…
  arxiv Teng Xiao, Yige Yuan, Zhengyu Chen, Mingxiao Li 等 2025-02-02T19:25:41Z 置信度 0.78 cs.LGcs.CL
• PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Association
  We study the task of learning association between faces and voices, which is gaining interest in the multimodal community lately. These methods suffer from the deliberate crafting of negative mining procedures as well as the reliance on the distant margin para…
  arxiv Abdul Hannan, Muhammad Arslan Manzoor, Shah Nawaz, Muhammad Irzam Liaqat 等 2025-05-22T17:57:55Z 置信度 0.78 cs.CVcs.AI
• The Pierre Auger Observatory: Contributions to the 39th International Cosmic Ray Conference (ICRC 2025)
  The Pierre Auger Observatory, located in La Pampa Amarilla, Argentina, has been continuously acquiring data since 2004. It comprises a surface detector array covering 3,000 km$^2$ and 27 fluorescence telescopes, designed to detect extensive air showers initiat…
  arxiv The Pierre Auger Collaboration, A. Abdul Halim, P. Abreu, M. Aglietta 等 2025-07-18T09:28:16Z 置信度 0.78 astro-ph.HEastro-ph.IM
• Team QUST at SemEval-2025 Task 10: Evaluating Large Language Models in Multiclass Multi-label Classification of News Entity Framing
  This paper describes the participation of QUST_NLP in the SemEval-2025 Task 7. We propose a three-stage retrieval framework specifically designed for fact-checked claim retrieval. Initially, we evaluate the performance of several retrieval models and select th…
  arxiv Jiyan Liu, Youzheng Liu, Taihang Wang, Xiaoman Xu 等 2025-06-12T07:09:35Z 置信度 0.78 cs.CLcs.AI
• RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection
  This study introduces RUMAA, a transformer-based framework for music performance analysis that unifies score-to-performance alignment, score-informed transcription, and mistake detection in a near end-to-end manner. Unlike prior methods addressing these tasks …
  arxiv Sungkyun Chang, Simon Dixon, Emmanouil Benetos 2025-07-16T12:13:13Z 置信度 0.78 cs.SDcs.CLcs.LGeess.AS
• IISE PG&E Energy Analytics Challenge 2025: Hourly-Binned Regression Models Beat Transformers in Load Forecasting
  Accurate electricity load forecasting is essential for grid stability, resource optimization, and renewable energy integration. While transformer-based deep learning models like TimeGPT have gained traction in time-series forecasting, their effectiveness in lo…
  arxiv Millend Roy, Vladimir Pyltsov, Yinbo Hu 2025-05-16T15:55:34Z 置信度 0.78 cs.LGecon.EMeess.SY
• Frictional Agent Alignment Framework: Slow Down and Don't Break Things
  AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the explicit signals of int…
  arxiv Abhijnan Nath, Carine Graff, Andrei Bachinin, Nikhil Krishnaswamy 2025-05-26T02:39:07Z 置信度 0.78 cs.CL
• Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
  Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutionizing cybersecurity, enabling both automa…
  arxiv Kiarash Ahi, Saeed Valizadeh 2026-07-08T03:40:26Z 置信度 0.78 cs.CRcs.AIcs.CL
• Implementation and Brief Experimental Analysis of the Duan et al. (2025) Algorithm for Single-Source Shortest Paths
  We present an implementation and experimental analysis of the deterministic algorithm proposed by Duan et al. (2025) for the Single-Source Shortest Path (SSSP) problem, which achieves the best-known asymptotic upper bound of $O(m \log^{2/3} n)$. We provide a w…
  arxiv Lucas Castro, Thailsson Clementino, Rosiane de Freitas 2025-11-04T21:18:44Z 置信度 0.78 cs.DS
• AKCIT-FN at CheckThat! 2025: Switching Fine-Tuned SLMs and LLM Prompting for Multilingual Claim Normalization
  Claim normalization, the transformation of informal social media posts into concise, self-contained statements, is a crucial step in automated fact-checking pipelines. This paper details our submission to the CLEF-2025 CheckThat! Task~2, which challenges syste…
  arxiv Fabrycio Leite Nakano Almada, Kauan Divino Pouso Mariano, Maykon Adriell Dutra, Victor Emanuel da Silva Monteiro 等 2025-09-15T01:19:49Z 置信度 0.78 cs.CL
• Temporal Alignment-Free Video Matching for Few-shot Action Recognition
  Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise video matching. While the frame- and tuple-level alignment approaches have been p…
  arxiv SuBeen Lee, WonJun Moon, Hyun Seok Seong, Jae-Pil Heo 2025-04-08T12:11:11Z 置信度 0.78 cs.CVcs.AI
• GPU Programming for AI Workflow Development on AWS SageMaker: An Instructional Approach
  We present the design, implementation, and comprehensive evaluation of a specialized course on GPU architecture, GPU programming, and how these are used for developing AI agents. This course is offered to undergraduate and graduate students during Fall 2024 an…
  arxiv Sriram Srinivasan, Hamdan Alabsi, Rand Obeidat, Nithisha Ponnala 等 2025-09-17T05:11:05Z 置信度 0.78 cs.DC
• Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts
  Time is implicitly embedded in classification process: classifiers are usually built on existing data while to be applied on future data whose distributions (e.g., label and token) may change. However, existing state-of-the-art classification models merely con…
  arxiv Weisi Liu, Guangzeng Han, Xiaolei Huang 2025-02-12T22:30:18Z 置信度 0.78 cs.CL
• DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis
  Multimodal sentiment analysis (MSA) integrates various modalities, such as text, image, and audio, to provide a more comprehensive understanding of sentiment. However, effective MSA is challenged by alignment and fusion issues. Alignment requires synchronizing…
  arxiv Yuhua Wen, Qifei Li, Yingying Zhou, Yingming Gao 等 2025-12-05T08:18:57Z 置信度 0.78 cs.CVcs.LG
• Ultimate Quantum Precision Limit at Colliders: Conditions and Case Studies
  We investigate whether collider experiments can reach the quantum limit of precision, defined by the quantum Fisher information (QFI), using only classical observables such as particle momenta. As a case study, we focus on the $τ^+τ^-$ system and the decay cha…
  arxiv Tengyu Ai, Qi Bi, Yuxin He, Jia Liu 等 2025-06-12T13:03:36Z 置信度 0.78 hep-phhep-exquant-ph
• Yi: Open Foundation Models by 01.AI
  We introduce the Yi model family, a series of language and multimodal models that demonstrate strong multi-dimensional capabilities. The Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context mo…
  arxiv 01. AI, :, Alex Young, Bei Chen 等 2024-03-07T16:52:49Z 置信度 0.78 cs.CLcs.AI
• Logits-Constrained Framework with RoBERTa for Ancient Chinese NER
  This paper presents a Logits-Constrained (LC) framework for Ancient Chinese Named Entity Recognition (NER), evaluated on the EvaHan 2025 benchmark. Our two-stage model integrates GujiRoBERTa for contextual encoding and a differentiable decoding mechanism to en…
  arxiv Wenjie Hua, Shenghan Xu 2025-05-05T19:23:16Z 置信度 0.78 cs.CL
• Content-Driven Local Response: Supporting Sentence-Level and Message-Level Mobile Email Replies With and Without AI
  Mobile emailing demands efficiency in diverse situations, which motivates the use of AI. However, generated text does not always reflect how people want to respond. This challenges users with AI involvement tradeoffs not yet considered in email UIs. We address…
  arxiv Tim Zindulka, Sven Goller, Florian Lehmann, Daniel Buschek 2025-02-10T13:06:25Z 置信度 0.78 cs.HCcs.CL
• Making the Right Thing: Bridging HCI and Responsible AI in Early-Stage AI Concept Selection
  AI projects often fail due to financial, technical, ethical, or user acceptance challenges -- failures frequently rooted in early-stage decisions. While HCI and Responsible AI (RAI) research emphasize this, practical approaches for identifying promising concep…
  arxiv Ji-Youn Jung, Devansh Saxena, Minjung Park, Jini Kim 等 2025-06-20T22:04:33Z 置信度 0.78 cs.HC
• Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
  Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious events reliably and tr…
  arxiv Luca Cotti, Anisa Rula, Devis Bianchini, Federico Cerutti 2025-08-26T23:17:33Z 置信度 0.78 cs.CRcs.AI
• AlphaPO: Reward Shape Matters for LLM Alignment
  Reinforcement Learning with Human Feedback (RLHF) and its variants have made huge strides toward the effective alignment of large language models (LLMs) to follow instructions and reflect human values. More recently, Direct Alignment Algorithms (DAAs) have eme…
  arxiv Aman Gupta, Shao Tang, Qingquan Song, Sirou Zhu 等 2025-01-07T15:46:42Z 置信度 0.78 cs.CL
• AI Model Passport: Data and System Traceability Framework for Transparent AI in Health
  The increasing integration of Artificial Intelligence (AI) into health and biomedical systems necessitates robust frameworks for transparency, accountability, and ethical compliance. Existing frameworks often rely on human-readable, manual documentation which …
  arxiv Varvara Kalokyri, Nikolaos S. Tachos, Charalampos N. Kalantzopoulos, Stelios Sfakianakis 等 2025-06-27T16:16:15Z 置信度 0.78 cs.AI
• Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
  Self-consistency improves reasoning by aggregating diverse stochastic samples, yet the dynamics behind its efficacy remain underexplored. We reframe self-consistency as a dynamic distributional alignment problem, revealing that decoding temperature not only go…
  arxiv Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan 等 2025-02-27T07:07:40Z 置信度 0.78 cs.CLcs.AI
• Density-Informed VAE (DiVAE): Reliable Log-Prior Probability via Density Alignment Regularization
  We introduce Density-Informed VAE (DiVAE), a lightweight, data-driven regularizer that aligns the VAE log-prior probability $\log p_Z(z)$ with a log-density estimated from data. Standard VAEs match latents to a simple prior, overlooking density structure in th…
  arxiv Michele Alessi, Alessio Ansuini, Alex Rodriguez 2025-12-03T16:27:23Z 置信度 0.78 cs.LG
• Towards Transformer-Based Aligned Generation with Self-Coherence Guidance
  We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-…
  arxiv Shulei Wang, Wang Lin, Hai Huang, Hanting Wang 等 2025-03-22T07:03:57Z 置信度 0.78 cs.CV
• Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards
  There has been increasing research interest in AI/ML for social impact, and correspondingly more publication venues have refined review criteria for practice-driven AI/ML research. However, these review guidelines tend to most concretely recognize projects tha…
  arxiv Bryan Wilder, Angela Zhou 2025-10-21T02:51:03Z 置信度 0.78 cs.LGcs.CY
• What Needs Attention? Prioritizing Drivers of Developers' Trust and Adoption of Generative AI
  Generative AI (genAI) tools promise productivity gains, yet miscalibrated trust and usage friction still hinder adoption. Moreover, genAI can be exclusionary, failing to adequately support diverse users. One such aspect of diversity is cognitive diversity, whi…
  arxiv Rudrajit Choudhuri, Bianca Trinkenreich, Rahul Pandita, Eirini Kalliamvakou 等 2025-05-23T03:05:56Z 置信度 0.78 cs.HCcs.SE
• AI in Popular Culture
  This book examines the transformative impact of generative AI on cultural production, with a particular focus on how AI technologies like ChatGPT are reshaping the creation of popular culture. Through a comprehensive analysis of both Global North and South per…
  crossref Dal Yong Jin 2025-10-17T08:56:11Z 置信度 0.70
• ODEI: Object Detector Efficiency Index
  Object detectors often rely on multiple metrics to reflect their accuracy and speed performances independently. This article introduces object detector efficiency index (ODEI), a hardware-agnostic metric designed to assess object detector efficiency based on s…
  crossref Wenan Yuan 2025-07-01T04:04:22Z 置信度 0.70
• ASSIGN—Ownership in the Age of AI
  Ownership, introduced in Chapter 5 , “Ownership as a Security Control,” is the bedrock of identity hygiene. When applied to AI identities, the same principle becomes far more urgent—and far harder to enforce. Let’s see how it is implemented here as a continuou…
  crossref Rosario Mastrogiacomo 2026-01-02T01:13:57Z 置信度 0.70