AI 安全与对齐 · 全部实体（第 43 / 100 页）

本页收录第 4201–4300 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Reconceptualising literacy as co-literacy in language education with AI
  This chapter explores a fundamental question for language education in the age of artificial intelligence: What does literacy mean when machines can write? As Kalantzis and Cope (2025) provocatively challenge us to consider, this technological shift requires a…
  crossref Antonie Alm 2025-04-30T04:56:26Z 置信度 0.70
• Human-AI Collaboration and the Future of Work
  This book was written with AI, with AI—not by AI. That distinction is everything. As we look ahead to the future of human-AI collaboration, we must clarify who leads, who owns, and who remains responsible.
  crossref Rosario Mastrogiacomo 2026-01-02T01:20:50Z 置信度 0.70
• (Un)Civilizing the Paris Olympics Opening Ceremony: Competing Narratives of Civilization, “Coloniality,” and Transversal Alignment
  Abstract Scholarship on “non-Western” civilizational discourse in international relations remains largely limited to the versions crafted or endorsed by the state. This paper takes the representation of the Paris Olympics opening ceremony on Chinese social med…
  crossref Chenchen Zhang 2025-11-21T14:53:54Z 置信度 0.70
• GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
  Aerial-Ground person re-identification (AG-ReID) is an emerging yet challenging task that aims to match pedestrian images captured from drastically different viewpoints, typically from unmanned aerial vehicles (UAVs) and ground-based surveillance cameras. The …
  arxiv Qiao Li, Jie Li, Yukang Zhang, Lei Tan 等 2025-10-25T12:16:10Z 置信度 0.78 cs.CV
• Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
  As AI research surges in both impact and volume, conferences have imposed submission limits to maintain paper quality and alleviate organizational pressure. In this work, we examine the fairness of desk-rejection systems under submission limits and reveal that…
  arxiv Yuefan Cao, Xiaoyu Li, Yingyu Liang, Zhizhou Sha 等 2025-02-02T06:29:23Z 置信度 0.78 cs.LGcs.AIcs.CYcs.DL
• Fast PINN Eigensolvers via Biconvex Reformulation
  Eigenvalue problems have a distinctive forward-inverse structure and are fundamental to characterizing a system's thermal response, stability, and natural modes. Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative for solving such problems b…
  arxiv Akshay Sai Banderwaar, Abhishek Gupta 2025-11-02T04:04:54Z 置信度 0.78 cs.LGcs.AIcs.NE
• Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications
  The design and application of LLM-based personas in AI companionship is a rapidly expanding but fragmented field, spanning from virtual emotional companions and game NPCs to embodied functional robots. This diversity in objectives, modality, and technical stac…
  arxiv Esther Sun, Zichu Wu 2025-11-04T20:37:13Z 置信度 0.78 cs.HCcs.AI
• Dynamite: Real-Time Debriefing Slide Authoring through AI-Enhanced Multimodal Interaction
  Facilitating class-wide debriefings after small-group discussions is a common strategy in ethics education. Instructor interviews revealed that effective debriefings should highlight frequently discussed themes and surface underrepresented viewpoints, making a…
  arxiv Panayu Keelawat, David Barron, Kaushik Narasimhan, Daniel Manesh 等 2025-07-27T05:48:49Z 置信度 0.78 cs.HC
• A Conceptual Model for AI Adoption in Financial Decision-Making: Addressing the Unique Challenges of Small and Medium-Sized Enterprises
  The adoption of artificial intelligence (AI) offers transformative potential for small and medium-sized enterprises (SMEs), particularly in enhancing financial decision-making processes. However, SMEs often face significant barriers to implementing AI technolo…
  arxiv Manh Chien Vu, Thang Le Dinh, Manh Chien Vu, Tran Duc Le 等 2025-12-03T23:57:34Z 置信度 0.78 cs.AI
• BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet)
  Test-time scaling is a family of techniques to improve LLM outputs at inference time by performing extra computation. To the best of our knowledge, test-time scaling has been limited to domains with verifiably correct answers, like mathematics and coding. We t…
  arxiv Tomas Ruiz, Siyao Peng, Barbara Plank, Carsten Schwemmer 2025-10-14T13:43:08Z 置信度 0.78 cs.CLcs.AI
• LABIIUM: AI-Enhanced Zero-configuration Measurement Automation System
  The complexity of laboratory environments requires solutions that simplify instrument interaction and enhance measurement automation. Traditional tools often require configuration, software, and programming skills, creating barriers to productivity. Previous a…
  arxiv Emmanuel A. Olowe, Danial Chitnis 2024-12-07T00:15:24Z 置信度 0.78 cs.AIcs.CLcs.HCcs.SE
• CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
  Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture-independent questions across languages,…
  arxiv Yumeng Wang, Zhiyuan Fan, Qingyun Wang, May Fung 等 2025-01-30T16:15:38Z 置信度 0.78 cs.CL
• Integrating Generative AI into Cybersecurity Education: A Study of OCR and Multimodal LLM-assisted Instruction
  This full paper describes an LLM-assisted instruction integrated with a virtual cybersecurity lab platform. The digital transformation of Fourth Industrial Revolution (4IR) systems is reshaping workforce needs, widening skill gaps, especially among older worke…
  arxiv Karan Patel, Yu-Zheng Lin, Gaurangi Raul, Bono Po-Jen Shih 等 2025-09-03T04:16:50Z 置信度 0.78 cs.CYcs.CR
• Soft Gravitons, Hard Truths: Infrared Safety of Particle Processes in a Gravitational-Wave Background
  Gravitational waves are thought to propagate unattenuated through matter due to a cancellation between graviton absorption and stimulated emission inferred from leading-order soft-graviton arguments. We revisit this reasoning and show that it fails for the con…
  arxiv Wen-Yuan Ai, Sebastian A. R. Ellis, Josef Pradler 2025-10-31T17:59:03Z 置信度 0.78 hep-phhep-th
• PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
  The convergence of artificial AI and XR technologies (AI XR) promises innovative applications across many domains. However, the sensitive nature of data (e.g., eye-tracking) used in these systems raises significant privacy concerns, as adversaries can exploit …
  arxiv Ripan Kumar Kundu, Istiak Ahmed, Khaza Anuarul Hoque 2025-12-18T18:23:06Z 置信度 0.78 cs.CRcs.AIcs.HC
• Twill: Scheduling Compound AI Systems on Heterogeneous Mobile Edge Platforms
  Compound AI (cAI) systems chain multiple AI models to solve complex problems. cAI systems are typically composed of deep neural networks (DNNs), transformers, and large language models (LLMs), exhibiting a high degree of computational diversity and dynamic wor…
  arxiv Zain Taufique, Aman Vyas, Antonio Miele, Pasi Liljeberg 等 2025-07-01T07:06:45Z 置信度 0.78 cs.MAcs.AIcs.CVcs.PF
• T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback
  Text-to-audio (T2A) generation has achieved remarkable progress in generating a variety of audio outputs from language prompts. However, current state-of-the-art T2A models still struggle to satisfy human preferences for prompt-following and acoustic quality w…
  arxiv Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang 等 2025-05-15T17:59:29Z 置信度 0.78 cs.SDeess.AS
• InfoPO: On Mutual Information Maximization for Large Language Model Alignment
  We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward models and online samp…
  arxiv Teng Xiao, Zhen Ge, Sujay Sanghavi, Tian Wang 等 2025-05-13T12:37:48Z 置信度 0.78 cs.LG
• AI and analytics in sports: Leveraging BERTopic to map the past and chart the future
  Purpose: The purpose of this study is to map the body of scholarly literature at the intersection of artificial intelligence (AI), analytics and sports and thereafter, leverage the insights generated to chart guideposts for future research. Design/methodology/…
  arxiv Manit Mishra 2025-10-17T09:57:42Z 置信度 0.78 stat.APcs.LG
• Speak & Improve Challenge 2025: Tasks and Baseline Systems
  This paper presents the "Speak & Improve Challenge 2025: Spoken Language Assessment and Feedback" -- a challenge associated with the ISCA SLaTE 2025 Workshop. The goal of the challenge is to advance research on spoken language assessment and feedback, with…
  arxiv Mengjie Qian, Kate Knill, Stefano Banno, Siyuan Tang 等 2024-12-16T17:05:18Z 置信度 0.78 cs.CL
• Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation
  Detecting small drones, often indistinguishable from birds, is crucial for modern surveillance. This work introduces a drone detection methodology built upon the medium-sized YOLOv11 object detection model. To enhance its performance on small targets, we imple…
  arxiv Rayson Laroca, Marcelo dos Santos, David Menotti 2025-04-27T20:06:55Z 置信度 0.78 cs.CV
• Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Models
  Reinforcement learning (RL) algorithms have been used recently to align diffusion models with downstream objectives such as aesthetic quality and text-image consistency by fine-tuning them to maximize a single reward function under a fixed KL regularization. H…
  arxiv Min Cheng, Fatemeh Doudi, Dileep Kalathil, Mohammad Ghavamzadeh 等 2025-05-24T06:27:55Z 置信度 0.78 cs.AIcs.CV
• A Critical Analysis of Affirmative Action and Academic Performance: A Response to the Preprint Authored by Matheus et al. (2025)
  This article offers a critical response to the preprint by Matheus et al. (2025), which evaluates the academic performance of students admitted through different entry routes at Sao Paulo State University. Although the dataset compiled by the authors is valuab…
  arxiv Claudio Andre Barbosa de Lira, Ricardo Borges Viana 2025-12-02T14:55:02Z 置信度 0.78 physics.ed-ph
• Public Constitutional AI
  We are increasingly subjected to the power of AI authorities. As AI decisions become inescapable, entering domains such as healthcare, education, and law, we must confront a vital question: how can we ensure AI systems have the legitimacy necessary for effecti…
  arxiv Gilad Abiri 2024-06-24T15:00:01Z 置信度 0.78 cs.CYcs.AI
• Bridging Generations using AI-Supported Co-Creative Activities
  Intergenerational co-creation using technology between grandparents and grandchildren can be challenging due to differences in technological familiarity. AI has emerged as a promising tool to support co-creative activities, offering flexibility and creative as…
  arxiv Callie Y. Kim, Arissa J. Sato, Nathan Thomas White, Hui-Ru Ho 等 2025-03-03T03:59:57Z 置信度 0.78 cs.HC
• "All Roads Lead to ChatGPT": How Generative AI is Eroding Social Interactions and Student Learning Communities
  The widespread adoption of generative AI is already impacting learning and help-seeking. While the benefits of generative AI are well-understood, recent studies have also raised concerns about increased potential for cheating and negative impacts on students' …
  arxiv Irene Hou, Owen Man, Kate Hamilton, Srishty Muthusekaran 等 2025-04-14T00:40:58Z 置信度 0.78 cs.CYcs.AIcs.HC
• Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
  Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in cold-start scenarios and lo…
  arxiv Weixiang Zhao, Xingyu Sui, Yulin Hu, Jiahe Guo 等 2025-05-21T12:38:36Z 置信度 0.78 cs.CL
• Towards Full Authorship with AI: Supporting Revision with AI-Generated Views
  Large language models (LLMs) are shaping a new user interface (UI) paradigm in writing tools by enabling users to generate text through prompts. This paradigm shifts some creative control from the user to the system, thereby diminishing the user's authorship a…
  arxiv Jiho Kim, Ray C. Flanagan, Noelle E. Haviland, ZeAi Sun 等 2024-03-02T01:11:35Z 置信度 0.78 cs.HCcs.AIcs.CY
• Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations
  Large language models (LLMs) show promise for personalized financial recommendations but are hampered by context limits, hallucinations, and a lack of behavioral grounding. Our prior work, FLARKO, embedded structured knowledge graphs (KGs) in LLM prompts to al…
  arxiv Fernando Spadea, Oshani Seneviratne 2025-10-08T20:42:53Z 置信度 0.78 cs.LGcs.AIcs.IR
• CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
  Vision-Language Models (VLMs) excel across diverse tasks but suffer from high inference costs in time and memory. Token sparsity mitigates inefficiencies in token usage, while neuron sparsity reduces high-dimensional computations, both offering promising solut…
  arxiv Qinsi Wang, Hancheng Ye, Ming-Yu Chung, Yudong Liu 等 2025-05-25T17:16:34Z 置信度 0.78 cs.LGcs.CV
• Securing Agentic AI Systems -- A Multilayer Security Framework
  Securing Agentic Artificial Intelligence (AI) systems requires addressing the complex cyber risks introduced by autonomous, decision-making, and adaptive behaviors. Agentic AI systems are increasingly deployed across industries, organizations, and critical sec…
  arxiv Sunil Arora, John Hastings 2025-12-19T20:22:25Z 置信度 0.78 cs.CRcs.AIcs.CY
• AI-induced sexual harassment: Investigating Contextual Characteristics and User Reactions of Sexual Harassment by a Companion Chatbot
  Advancements in artificial intelligence (AI) have led to the increase of conversational agents like Replika, designed to provide social interaction and emotional support. However, reports of these AI systems engaging in inappropriate sexual behaviors with user…
  arxiv Mohammad, Namvarpour, Harrison Pauwels, Afsaneh Razi 2025-04-05T23:04:37Z 置信度 0.78 cs.HCcs.AI
• Non-native Children's Automatic Speech Assessment Challenge (NOCASA)
  This paper presents the "Non-native Children's Automatic Speech Assessment" (NOCASA) - a data competition part of the IEEE MLSP 2025 conference. NOCASA challenges participants to develop new systems that can assess single-word pronunciations of young second la…
  arxiv Yaroslav Getman, Tamás Grósz, Mikko Kurimo, Giampiero Salvi 2025-04-29T11:59:08Z 置信度 0.78 cs.CLeess.AS
• MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation
  Medical image reporting (MIR) aims to generate structured clinical descriptions from radiological images. Existing methods struggle with fine-grained feature extraction, multimodal alignment, and generalization across diverse imaging types, often relying on va…
  arxiv Amaan Izhar, Nurul Japar, Norisma Idris, Ting Dang 2025-04-29T01:26:02Z 置信度 0.78 cs.CV
• A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications
  Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with universal human values. Cur…
  arxiv Jian Guan, Junfei Wu, Jia-Nan Li, Chuanqi Cheng 等 2025-03-21T10:09:16Z 置信度 0.78 cs.CL
• STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls
  The rapid shift from stateless large language models (LLMs) to autonomous, goal-driven agents raises a central question: When is agentic AI truly necessary? While agents enable multi-step reasoning, persistent memory, and tool orchestration, deploying them ind…
  arxiv Shubhi Asthana, Bing Zhang, Chad DeLuca, Ruchi Mahindru 等 2025-12-01T21:54:07Z 置信度 0.78 cs.AIcs.LG
• Z-Stack Scanning can Improve AI Detection of Mitosis: A Case Study of Meningiomas
  Z-stack scanning is an emerging whole slide imaging technology that captures multiple focal planes alongside the z-axis of a glass slide. Because z-stacking can offer enhanced depth information compared to the single-layer whole slide imaging, this technology …
  arxiv Hongyan Gu, Ellie Onstott, Wenzhong Yan, Tengyou Xu 等 2025-01-27T03:09:58Z 置信度 0.78 eess.IVcs.CV
• QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
  Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety alignment are developed for …
  arxiv Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan 等 2025-02-13T19:13:03Z 置信度 0.78 cs.CRcs.AIcs.CL
• SCENEFORGE: Enhancing 3D-text alignment with Structured Scene Compositions
  The whole is greater than the sum of its parts-even in 3D-text contrastive learning. We introduce SceneForge, a novel framework that enhances contrastive alignment between 3D point clouds and text through structured multi-object scene compositions. SceneForge …
  arxiv Cristian Sbrolli, Matteo Matteucci 2025-09-19T07:13:45Z 置信度 0.78 cs.CVcs.MM
• DICE: Data Influence Cascade in Decentralized Learning
  Decentralized learning offers a promising approach to crowdsource data consumptions and computational workloads across geographically distributed compute interconnected through peer-to-peer networks, accommodating the exponentially increasing demands. However,…
  arxiv Tongtian Zhu, Wenhao Li, Can Wang, Fengxiang He 2025-07-09T15:13:44Z 置信度 0.78 cs.LGcs.DCcs.MAcs.SIstat.ML
• FedPPA: Progressive Parameter Alignment for Personalized Federated Learning
  Federated Learning (FL) is designed as a decentralized, privacy-preserving machine learning paradigm that enables multiple clients to collaboratively train a model without sharing their data. In real-world scenarios, however, clients often have heterogeneous c…
  arxiv Maulidi Adi Prasetia, Muhamad Risqi U. Saputra, Guntur Dharma Putra 2025-10-16T14:03:05Z 置信度 0.78 cs.LGcs.AI
• Aligning Moments in Time using Video Queries
  Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling complex dependencies betw…
  arxiv Yogesh Kumar, Uday Agarwal, Manish Gupta, Anand Mishra 2025-08-21T11:01:13Z 置信度 0.78 cs.CV
• Explainable AI Components for Narrative Map Extraction
  As narrative extraction systems grow in complexity, establishing user trust through interpretable and explainable outputs becomes increasingly critical. This paper presents an evaluation of an Explainable Artificial Intelligence (XAI) system for narrative map …
  arxiv Brian Keith, Fausto German, Eric Krokos, Sarah Joseph 等 2025-03-19T17:48:00Z 置信度 0.78 cs.CLcs.HC
• Lifecycle Management of Trustworthy AI Models in 6G Networks: The REASON Approach
  Artificial Intelligence (AI) is expected to play a key role in 6G networks including optimising system management, operation, and evolution. This requires systematic lifecycle management of AI models, ensuring their impact on services and stakeholders is conti…
  arxiv Juan Parra-Ullauri, Xueqing Zhou, Shadi Moazzeni, Rasheed Hussain 等 2025-04-03T08:56:29Z 置信度 0.78 cs.NI
• Towards Improving Speaker Distance Estimation through Generative Impulse Response Augmentation
  The Room Acoustics and Speaker Distance Estimation (SDE) Challenge at ICASSP 2025 explores the effectiveness of augmented room impulse response (RIR) data for improving SDE model performance. This challenge at GenDARA involves generating RIRs to supplement spa…
  arxiv Anton Ratnarajah, Mehmet Ergezer, Arun Nair, Mrudula Athi 2026-05-01T15:08:42Z 置信度 0.78 cs.SDcs.AIeess.ASeess.SP
• Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions
  A growing body of work in Ethical AI attempts to capture human moral judgments through simple computational models. The key question we address in this work is whether such simple AI models capture {the critical} nuances of moral decision-making by focusing on…
  arxiv Vijay Keswani, Vincent Conitzer, Walter Sinnott-Armstrong, Breanna K. Nguyen 等 2025-03-02T15:42:17Z 置信度 0.78 cs.HCcs.AIcs.CY
• ABC-GS: Alignment-Based Controllable Style Transfer for 3D Gaussian Splatting
  3D scene stylization approaches based on Neural Radiance Fields (NeRF) achieve promising results by optimizing with Nearest Neighbor Feature Matching (NNFM) loss. However, NNFM loss does not consider global style information. In addition, the implicit represen…
  arxiv Wenjie Liu, Zhongliang Liu, Xiaoyan Yang, Man Sha 等 2025-03-28T08:07:57Z 置信度 0.78 cs.CVeess.IV
• QU-NLP at CheckThat! 2025: Multilingual Subjectivity in News Articles Detection using Feature-Augmented Transformer Models with Sequential Cross-Lingual Fine-Tuning
  This paper presents our approach to the CheckThat! 2025 Task 1 on subjectivity detection, where systems are challenged to distinguish whether a sentence from a news article expresses the subjective view of the author or presents an objective view on the covere…
  arxiv Mohammad AL-Smadi 2025-07-01T13:39:59Z 置信度 0.78 cs.CL
• A Coopetitive-Compatible Data Generation Framework for Cross-silo Federated Learning
  Cross-silo federated learning (CFL) enables organizations (e.g., hospitals or banks) to collaboratively train artificial intelligence (AI) models while preserving data privacy by keeping data local. While prior work has primarily addressed statistical heteroge…
  arxiv Thanh Linh Nguyen, Quoc-Viet Pham 2025-09-10T13:29:05Z 置信度 0.78 cs.LGcs.AIcs.CEcs.DCcs.GT
• Zero-shot Inexact CAD Model Alignment from a Single Image
  One practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image. Existing methods rely on supervised training with images and pose annotations, which li…
  arxiv Pattaramanee Arsomngern, Sasikarn Khwanmuang, Matthias Nießner, Supasorn Suwajanakorn 2025-07-04T04:46:59Z 置信度 0.78 cs.CV
• Malaysia's AI-Driven Education Landscape: Policies, Applications, and Comparative Insights for a Digital Future
  Artificial Intelligence (AI) is transforming education globally, and Malaysia is leveraging this potential through strategic policies to enhance learning and prepare students for a digital future. This article explores Malaysia's AI-driven education landscape,…
  arxiv Fadhilah Jamaluddin, Ahmad Hakiim Jamaluddin, Faridzah Jamaluddin, Faathirah Jamaluddin 2025-09-26T04:33:37Z 置信度 0.78 cs.CY
• Human and Machine: How Software Engineers Perceive and Engage with AI-Assisted Code Reviews Compared to Their Peers
  The integration of artificial intelligence (AI) continues to increase and evolve, including in software engineering (SE). This integration involves processes traditionally entrusted to humans, such as coding. However, the impact on socio-technical processes li…
  arxiv Adam Alami, Neil A. Ernst 2025-01-03T20:42:51Z 置信度 0.78 cs.SE
• Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4
  Cross-modal drone navigation remains a challenging task in robotics, requiring efficient retrieval of relevant images from large-scale databases based on natural language descriptions. The RoboSense 2025 Track 4 challenge addresses this challenge, focusing on …
  arxiv Lingfeng Zhang, Erjia Xiao, Yuchen Zhang, Haoxiang Fu 等 2025-10-03T05:13:19Z 置信度 0.78 cs.RO
• Generative AI as a Pillar for Predicting 2D and 3D Wildfire Spread: Beyond Physics-Based Models and Traditional Deep Learning
  Wildfires increasingly threaten human life, ecosystems, and infrastructure, with events like the 2025 Palisades and Eaton fires in Los Angeles County underscoring the urgent need for more advanced prediction frameworks. Existing physics-based and deep learning…
  arxiv Haowen Xu, Sisi Zlatanova, Ruiyu Liang, Ismet Canbulat 2025-06-03T05:54:40Z 置信度 0.78 cs.AIcs.CE
• Solutions with expanding compact support of saturated Schr{ö}dinger equations: self-similar solutions
  We prove the existence of solutions \(u(t,x)\) of the Schr{ö}dinger equation with a saturation nonlinear term \((u/|u|)\) having compact support, for each \(t>0,\) that expands with a growth law of the type \(C\sqrt{t}\). The primary tool is considering the…
  arxiv Pascal Bégout, Jesus Ildefonso Diaz 2025-06-05T07:14:50Z 置信度 0.78 math.AP
• AI-to-AI Code Reviews of GitHub Pull Requests
  AI coding agents are increasingly integrated into software development workflows, operating on both sides of the pull-request (PR) process: AI authoring agents create or modify PRs, while AI reviewers evaluate them. This creates a closed loop in which one AI c…
  arxiv Niruthiha Selvanayagam, Taher A. Ghaleb 2026-08-21T17:17:35Z 置信度 0.78 cs.SE
• Supporting Preschool Emotional Development with AI-Powered Robots
  This study evaluates the integration of AI-powered robots in early childhood education, focusing on their impact on emotional self-regulation, engagement, and collaborative skills. A ten-week experimental design involving two groups of children assessed the ro…
  arxiv Santiago Berrezueta-Guzman, María Dolón-Poza, Stefan Wagner 2025-05-24T11:53:43Z 置信度 0.78 cs.ROcs.HC
• When AI Democratizes Exploitation: LLM-Assisted Strategic Manipulation of Fair Division Algorithms
  Fair resource division algorithms, like those implemented in Spliddit platform, have traditionally been considered difficult for the end users to manipulate due to its complexities. This paper demonstrates how Large Language Models (LLMs) can dismantle these p…
  arxiv Priyanka Verma, Balagopal Unnikrishnan 2025-11-18T18:09:02Z 置信度 0.78 cs.CYecon.GN
• SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations
  Semantic correspondence made tremendous progress through the recent advancements of large vision models (LVM). While these LVMs have been shown to reliably capture local semantics, the same can currently not be said for capturing global geometric relationships…
  arxiv Krispin Wandel, Hesheng Wang 2025-03-28T14:14:19Z 置信度 0.78 cs.CV
• An Empirical Inquiry into Surveillance Capitalism: Web Tracking
  The modern web is increasingly characterized by the pervasiveness of Surveillance Capitalism. This investigation employs an empirical approach to examine this phenomenon through the web tracking practices of major tech companies -- specifically Google, Apple, …
  arxiv Nils Bonfils 2025-08-10T18:46:43Z 置信度 0.78 cs.CY
• VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication
  Trust plays a fundamental role in shaping the willingness of users to engage and collaborate with artificial intelligence (AI) systems. Yet, measuring user trust remains challenging due to its complex and dynamic nature. While traditional survey methods provid…
  arxiv Xin Wang, Stephanie Tulk Jesso, Sadamori Kojaku, David M Neyens 等 2025-03-10T13:00:41Z 置信度 0.78 cs.HCcs.AIcs.CL
• Benchmarking is Broken -- Don't Let AI be its Own Judge
  The meteoric rise of AI, with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need for a new, unified paradigm for trustworthy evaluation, as current benchmarks in…
  arxiv Zerui Cheng, Stella Wohnig, Ruchika Gupta, Samiul Alam 等 2025-10-08T21:41:37Z 置信度 0.78 cs.AIcs.LG
• MAPS: Multi-Fidelity AI-Augmented Photonic Simulation and Inverse Design Infrastructure
  Inverse design has emerged as a transformative approach for photonic device optimization, enabling the exploration of high-dimensional, non-intuitive design spaces to create ultra-compact devices and advance photonic integrated circuits (PICs) in computing and…
  arxiv Pingchuan Ma, Zhengqi Gao, Meng Zhang, Haoyu Yang 等 2025-03-02T22:30:18Z 置信度 0.78 physics.opticscs.AIcs.ET
• Debunking the CUDA Myth Towards GPU-based AI Systems
  This paper presents a comprehensive evaluation of Intel Gaudi NPUs as an alternative to NVIDIA GPUs, which is currently the de facto standard in AI system design. First, we create a suite of microbenchmarks to compare Intel Gaudi-2 with NVIDIA A100, showing th…
  arxiv Yunjae Lee, Juntaek Lim, Jehyeon Bang, Eunyeong Cho 等 2024-12-31T01:24:52Z 置信度 0.78 cs.DCcs.AIcs.AR
• AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results
  This paper reviews the AIS 2024 Video Quality Assessment (VQA) Challenge, focused on User-Generated Content (UGC). The aim of this challenge is to gather deep learning-based methods capable of estimating the perceptual quality of UGC videos. The user-generated…
  arxiv Marcos V. Conde, Saman Zadtootaghaj, Nabajeet Barman, Radu Timofte 等 2024-04-24T21:02:14Z 置信度 0.78 cs.CVcs.MM
• Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
  The Model Context Protocol (MCP) represents a significant advancement in AI-tool integration, enabling seamless communication between AI agents and external services. However, this connectivity introduces novel attack vectors that remain largely unexplored. Th…
  arxiv Nicola Croce, Tobin South 2025-07-26T09:22:40Z 置信度 0.78 cs.CRcs.AI
• GLAM: Geometry-Guided Local Alignment for Multi-View VLP in Mammography
  Mammography screening is an essential tool for early detection of breast cancer. The speed and accuracy of mammography interpretation have the potential to be improved with deep learning methods. However, the development of a foundation visual language model (…
  arxiv Yuexi Du, Lihui Chen, Nicha C. Dvornek 2025-09-12T15:33:18Z 置信度 0.78 cs.CVcs.AIcs.LG
• The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs) on reasoning tasks that elicit emergent long chains of thought (CoTs). Unlike supervised learning, it updates the model using both correct and inco…
  arxiv Xinyu Zhu, Mengzhou Xia, Zhepei Wei, Wei-Lin Chen 等 2025-06-02T06:10:54Z 置信度 0.78 cs.CLcs.LG
• On the creation of narrow AI: hierarchy and nonlocality of neural network skills
  We study the problem of creating strong, yet narrow, AI systems. While recent AI progress has been driven by the training of large general-purpose foundation models, the creation of smaller models specialized for narrow domains could be valuable for both effic…
  arxiv Eric J. Michaud, Asher Parker-Sartori, Max Tegmark 2025-05-21T17:59:21Z 置信度 0.78 cs.LG
• ViTA-PAR: Visual and Textual Attribute Alignment with Attribute Prompting for Pedestrian Attribute Recognition
  The Pedestrian Attribute Recognition (PAR) task aims to identify various detailed attributes of an individual, such as clothing, accessories, and gender. To enhance PAR performance, a model must capture features ranging from coarse-grained global attributes (e…
  arxiv Minjeong Park, Hongbeen Park, Jinkyu Kim 2025-06-02T08:07:06Z 置信度 0.78 cs.CVcs.AI
• Evaluating Open-Source Vision-Language Models for Multimodal Sarcasm Detection
  Recent advances in open-source vision-language models (VLMs) offer new opportunities for understanding complex and subjective multimodal phenomena such as sarcasm. In this work, we evaluate seven state-of-the-art VLMs - BLIP2, InstructBLIP, OpenFlamingo, LLaVA…
  arxiv Saroj Basnet, Shafkat Farabi, Tharindu Ranasinghe, Diptesh Kanoji 等 2025-10-13T19:05:21Z 置信度 0.78 cs.LG
• A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
  This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We introduce a comprehensive e…
  arxiv Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki 2025-12-09T16:39:32Z 置信度 0.78 cs.CLcs.AI
• A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation
  As large language models demonstrate enormous potential in the field of Electronic Design Automation (EDA), generative AI-assisted chip design is attracting widespread attention from academia and industry. Although these technologies have made preliminary prog…
  arxiv Wenbo Liu, Forbes Hou, Jon Zhang, Hong Liu 等 2025-07-29T11:17:47Z 置信度 0.78 cs.ARcs.AI
• ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness Prediction via Human-AI Collaborative Annotation
  Multimodal Review Helpfulness Prediction (MRHP) is an essential task in recommender systems, particularly in E-commerce platforms. Determining the helpfulness of user-generated reviews enhances user experience and improves consumer decision-making. However, ex…
  arxiv Truc Mai-Thanh Nguyen, Dat Minh Nguyen, Son T. Luu, Kiet Van Nguyen 2025-05-12T10:11:28Z 置信度 0.78 cs.CL
• Evolution of Programmers' Trust in Generative AI Programming Assistants
  Motivation. Trust in generative AI programming assistants is a vital attitude that impacts how programmers use those programming assistants. Programmers that are over-trusting may be too reliant on their tools, leading to incorrect or vulnerable code; programm…
  arxiv Anshul Shah, Thomas Rexin, Elena Tomson, Leo Porter 等 2025-09-16T17:06:47Z 置信度 0.78 cs.HCcs.SE
• Interaction-Required Suggestions for Control, Ownership, and Awareness in Human-AI Co-Writing
  This paper explores interaction designs for generative AI interfaces that necessitate human involvement throughout the generation process. We argue that such interfaces can promote cognitive engagement, agency, and thoughtful decision-making. Through a case st…
  arxiv Kenneth C. Arnold, Jiho Kim 2025-04-11T17:50:38Z 置信度 0.78 cs.HC
• Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
  This report investigates approaches for prompting a tool-augmented large language model (LLM) to act as a role-playing dialogue agent in the API track of the Commonsense Persona-grounded Dialogue Challenge (CPDC) 2025. In this setting, dialogue agents often pr…
  arxiv Saksorn Ruangtanusak, Pittawat Taveekitworachai, Kunat Pipatanakul 2025-08-30T12:45:36Z 置信度 0.78 cs.CLcs.AIcs.HC
• Episodic memory in AI agents poses risks that should be studied and mitigated
  Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future. The ability to form a…
  arxiv Chad DeChant 2025-01-20T20:54:06Z 置信度 0.78 cs.AIcs.CY
• Institutional Review Boards as Soft Governance Mechanisms of R&D: Governing the R&D of AI-based Medical Products
  Risk-based approaches to governance bear an ambiguous stance regarding the Research and Development stages of AI, for they the possibility of explicit risks before they are posed by a given finalised product. In this context, Institutional Review Boards (IRBs)…
  arxiv Antoni Lorente 2024-10-25T14:12:58Z 置信度 0.78 cs.CY
• Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
  Prior research on out-of-distribution detection (OoDD) has primarily focused on single-modality models. Recently, with the advent of large-scale pretrained vision-language models such as CLIP, OoDD methods utilizing such multi-modal representations through zer…
  arxiv Jeonghyeon Kim, Sangheum Hwang 2025-03-24T16:00:21Z 置信度 0.78 cs.CVcs.AI
• Payrolls to Prompts: Firm-Level Evidence on the Substitution of Labor for AI
  Generative AI has the potential to transform how firms produce output. Yet, credible evidence on how AI is actually substituting for human labor remains limited. In this paper, we study firm-level substitution between contracted online labor and generative AI …
  arxiv Ryan Stevens 2026-01-28T20:21:27Z 置信度 0.78 econ.GN
• DiffVLA++: Bridging Cognitive Reasoning and End-to-End Driving through Metric-Guided Alignment
  Conventional end-to-end (E2E) driving models are effective at generating physically plausible trajectories, but often fail to generalize to long-tail scenarios due to the lack of essential world knowledge to understand and reason about surrounding environments…
  arxiv Yu Gao, Anqing Jiang, Yiru Wang, Wang Jijun 等 2025-10-20T04:49:14Z 置信度 0.78 cs.ROcs.CV
• Assessing the Alignment of Audio Representations with Timbre Similarity Ratings
  Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scalability issues and are incapable of generalization. Recent results from audio (m…
  arxiv Haokun Tian, Stefan Lattner, Charalampos Saitis 2025-07-10T13:41:59Z 置信度 0.78 cs.SDeess.AS
• Dark-state photonic entanglement filters
  Preserving entanglement in the presence of decoherence remains a major challenge for quantum technologies. Recent proposals [M.A. Selim et al., Science 387, 1424 (2025)] have employed photonic filters based on anti-parity-time symmetry to recover certain entan…
  arxiv Stefano Longhi 2025-07-17T11:45:09Z 置信度 0.78 quant-phphysics.optics
• TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
  This paper introduces Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning (TARO), a novel framework for high-fidelity and temporally coherent video-to-audio synthesis. Built upon flow-based transformers, which offer stable training and con…
  arxiv Tri Ton, Ji Woo Hong, Chang D. Yoo 2025-04-08T04:49:36Z 置信度 0.78 cs.SDcs.AIcs.CV
• BoKDiff: Best-of-K Diffusion Alignment for Target-Specific 3D Molecule Generation
  Structure-based drug design (SBDD) leverages the 3D structure of biomolecular targets to guide the creation of new therapeutic agents. Recent advances in generative models, including diffusion models and geometric deep learning, have demonstrated promise in op…
  arxiv Ali Khodabandeh Yalabadi, Mehdi Yazdani-Jahromi, Ozlem Ozmen Garibay 2025-01-26T18:29:11Z 置信度 0.78 q-bio.BMcs.LG
• Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
  Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for finetuning, while dif…
  arxiv Johannes Schusterbauer, Ming Gui, Frank Fundel, Björn Ommer 2025-06-02T20:05:05Z 置信度 0.78 cs.CVcs.LG
• Wildfire Detection Using Vision Transformer with the Wildfire Dataset
  The critical need for sophisticated detection techniques has been highlighted by the rising frequency and intensity of wildfires in the US, especially in California. In 2023, wildfires caused 130 deaths nationwide, the highest since 1990. In January 2025, Los …
  arxiv Gowtham Raj Vuppari, Navarun Gupta, Ahmed El-Sayed, Xingguo Xiong 2025-05-23T02:08:28Z 置信度 0.78 cs.CVcs.AI
• No Masks Needed: Explainable AI for Deriving Segmentation from Classification
  Medical image segmentation is vital for modern healthcare and is a key element of computer-aided diagnosis. While recent advancements in computer vision have explored unsupervised segmentation using pre-trained models, these methods have not been translated we…
  arxiv Mosong Ma, Tania Stathaki, Michalis Lazarou 2025-08-06T15:18:00Z 置信度 0.78 cs.CV
• The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
  As the adoption of Generative AI in real-world services grow explosively, energy has emerged as a critical bottleneck resource. However, energy remains a metric that is often overlooked, under-explored, or poorly understood in the context of building ML system…
  arxiv Jae-Won Chung, Jeff J. Ma, Ruofan Wu, Jiachen Liu 等 2025-05-09T18:27:32Z 置信度 0.78 cs.LGcs.AI
• AI Ethics Education in India: A Syllabus-Level Review of Computing Courses
  The pervasive integration of artificial intelligence (AI) across domains such as healthcare, governance, finance, and education has intensified scrutiny of its ethical implications, including algorithmic bias, privacy risks, accountability, and societal impact…
  arxiv Anshu M Mittal, P D Parthasarathy, Swaroop Joshi 2025-09-26T13:24:01Z 置信度 0.78 cs.CY
• Building crypto portfolios with agentic AI
  The rapid growth of crypto markets has opened new opportunities for investors, but at the same time exposed them to high volatility. To address the challenge of managing dynamic portfolios in such an environment, this paper presents a practical application of …
  arxiv Antonino Castelli, Paolo Giudici, Alessandro Piergallini 2025-07-11T18:03:51Z 置信度 0.78 q-fin.PMcs.LG
• Representation Learning for Semantic Alignment of Language, Audio, and Visual Modalities
  This paper proposes a single-stage training approach that semantically aligns three modalities - audio, visual, and text using a contrastive learning framework. Contrastive training has gained prominence for multimodal alignment, utilizing large-scale unlabele…
  arxiv Parthasaarathy Sudarsanam, Irene Martín-Morató, Tuomas Virtanen 2025-05-20T16:21:27Z 置信度 0.78 cs.SDcs.MMeess.AS
• DATA: Domain-And-Time Alignment for High-Quality Feature Fusion in Collaborative Perception
  Feature-level fusion shows promise in collaborative perception (CP) through balanced performance and communication bandwidth trade-off. However, its effectiveness critically relies on input feature quality. The acquisition of high-quality features faces domain…
  arxiv Chengchang Tian, Jianwei Ma, Yan Huang, Zhanye Chen 等 2025-07-24T09:24:29Z 置信度 0.78 cs.CV
• Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average
  We report on the application of a high-capacity semantic segmentation pipeline to the GOOSE 2D Semantic Segmentation Challenge for unstructured off-road environments. Using a FlashInternImage-B backbone together with a UPerNet decoder, we adapt established tec…
  arxiv Wonjune Kim, Lae-kyoung Lee, Su-Yong An 2025-05-17T00:29:17Z 置信度 0.78 cs.CV
• A Survey of AI Scientists
  Artificial intelligence is undergoing a profound transition from a computational instrument to an autonomous originator of scientific knowledge. This emerging paradigm, the AI scientist, is architected to emulate the complete scientific workflow-from initial h…
  arxiv Guiyao Tie, Pan Zhou, Lichao Sun 2025-10-27T06:13:21Z 置信度 0.78 cs.AI
• AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting
  3D Gaussian Splatting (3DGS) has shown impressive results in real-time novel view synthesis. However, it often struggles under sparse-view settings, producing undesirable artifacts such as floaters, inaccurate geometry, and overfitting due to limited observati…
  arxiv Gurutva Patle, Nilay Girgaonkar, Nagabhushan Somraj, Rajiv Soundararajan 2025-09-13T23:05:49Z 置信度 0.78 cs.GRcs.CV
• Predicting Diabetic Retinopathy Using a Two-Level Ensemble Model
  Preprint Note: This is the author preprint version of a paper accepted for presentation at the IISE Annual Conference & Expo 2025. The final version will appear in the official proceedings. Diabetic retinopathy (DR) is a leading cause of blindness in worki…
  arxiv Mahyar Mahmoudi, Tieming Liu 2025-10-01T16:19:57Z 置信度 0.78 cs.LG
• Time Warp: The Gap Between Developers' Ideal vs Actual Workweeks in an AI-Driven Era
  Software developers balance a variety of different tasks in a workweek, yet the allocation of time often differs from what they consider ideal. Identifying and addressing these deviations is crucial for organizations aiming to enhance the productivity and well…
  arxiv Sukrit Kumar, Drishti Goel, Thomas Zimmermann, Brian Houck 等 2025-02-21T08:29:49Z 置信度 0.78 cs.SEcs.AIcs.HC
• Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid
  Generative Artificial Intelligence (GenAI) represents a rapidly expanding digital infrastructure whose energy demand and associated CO2 emissions are emerging as a new category of climate risk. This study introduces G-TRACE (GenAI Transformative Carbon Estimat…
  arxiv Zahida Kausar, Seemab Latif, Raja Khurram Shahzad, Mehwish Fatima 2025-11-06T19:52:02Z 置信度 0.78 cs.CYcs.CL