AI 安全与对齐 · 全部实体（第 90 / 100 页）

本页收录第 8901–9000 条，共 10000 条 · 返回 AI 安全与对齐 首页

• Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings
  Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions that do not reflect the realities of healthcare delivery in low-resource settings. This study presents the first …
  arxiv Anthonio Oladimeji Gabriel, Ahmad Rufai Yusuf 2026-05-16T13:33:47Z 置信度 0.78 cs.CYcs.AIcs.LG
• Exploring Self-Supervised Learning with U-Net Masked Autoencoders and EfficientNet-B7 for Improved Gastrointestinal Abnormality Classification in Video Capsule Endoscopy
  Video Capsule Endoscopy (VCE) has become an indispensable diagnostic tool for gastrointestinal (GI) disorders due to its non-invasive nature and ability to capture high-resolution images of the small intestine. However, the enormous volume of data generated du…
  arxiv Vamshi Krishna Kancharla, Pavan Kumar Kaveti, Dasari Naga Raju 2024-10-25T17:53:15Z 置信度 0.78 cs.CV
• Detecting Generative Parroting through Overfitting Masked Autoencoders
  The advent of generative AI models has revolutionized digital content creation, yet it introduces challenges in maintaining copyright integrity due to generative parroting, where models mimic their training data too closely. Our research presents a novel appro…
  arxiv Saeid Asgari Taghanaki, Joseph Lambourne 2024-03-27T23:10:33Z 置信度 0.78 cs.LGcs.AI
• The Wisdom of Deliberating AI Crowds: Does Deliberation Improve LLM-Based Forecasting?
  Structured deliberation has been found to improve the performance of human forecasters. This study investigates whether a similar intervention, i.e. allowing LLMs to review each other's forecasts before updating, can improve accuracy in large language models (…
  arxiv Paul Schneider, Amalie Schramm 2025-12-27T15:45:21Z 置信度 0.78 cs.AIcs.MA
• Subjective Experience in AI Systems: What Do AI Researchers and the Public Believe?
  We surveyed 582 AI researchers who have published in leading AI venues and 838 nationally representative US participants about their views on the potential development of AI systems with subjective experience and how such systems should be treated and governed…
  arxiv Noemi Dreksler, Lucius Caviola, David Chalmers, Carter Allen 等 2025-06-13T16:53:28Z 置信度 0.78 cs.CYcs.AI
• An Empirical Study of Vehicle Re-Identification on the AI City Challenge
  This paper introduces our solution for the Track2 in AI City Challenge 2021 (AICITY21). The Track2 is a vehicle re-identification (ReID) task with both the real-world data and synthetic data. We mainly focus on four points, i.e. training data, unsupervised dom…
  arxiv Hao Luo, Weihua Chen, Xianzhe Xu, Jianyang Gu 等 2021-05-20T12:20:52Z 置信度 0.78 cs.CV
• Fast Person Detection Using YOLOX With AI Accelerator For Train Station Safety
  Recently, Image processing has advanced Faster and applied in many fields, including health, industry, and transportation. In the transportation sector, object detection is widely used to improve security, for example, in traffic security and passenger crossin…
  arxiv Mas Nurul Achmadiah, Novendra Setyawan, Achmad Arif Bryantono, Chi-Chia Sun 等 2026-02-11T07:30:03Z 置信度 0.78 cs.CV
• Overview of BioASQ 2024: The twelfth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
  This is an overview of the twelfth edition of the BioASQ challenge in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2024. BioASQ is a series of international challenges promoting advances in large-scale biomedical semantic indexing and …
  arxiv Anastasios Nentidis, Georgios Katsimpras, Anastasia Krithara, Salvador Lima-López 等 2025-08-28T08:17:57Z 置信度 0.78 cs.CLcs.AIcs.IR
• Alignment as Jurisprudence
  Jurisprudence, the study of how judges should properly decide cases, and alignment, the science of getting AI models to conform to human values, share a fundamental structure. These seemingly distant fields both seek to predict and shape how decisions by power…
  arxiv Nicholas Caputo 2026-05-08T19:22:11Z 置信度 0.78 cs.AIcs.CYcs.LG
• Getting In Contract with Large Language Models -- An Agency Theory Perspective On Large Language Model Alignment
  Adopting Large language models (LLMs) in organizations potentially revolutionizes our lives and work. However, they can generate off-topic, discriminating, or harmful content. This AI alignment problem often stems from misspecifications during the LLM adoption…
  arxiv Sascha Kaltenpoth, Oliver Müller 2025-09-09T12:10:14Z 置信度 0.78 cs.AI
• Multimodal Datasets and Benchmarks for Reasoning about Dynamic Spatio-Temporality in Everyday Environments
  We used a 3D simulator to create artificial video data with standardized annotations, aiming to aid in the development of Embodied AI. Our question answering (QA) dataset measures the extent to which a robot can understand human behavior and the environment in…
  arxiv Takanori Ugai, Kensho Hara, Shusaku Egami, Ken Fukuda 2024-08-21T05:27:55Z 置信度 0.78 cs.AI
• Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment
  Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the generated output can c…
  arxiv Paarth Neekhara, Shehzeen Hussain, Subhankar Ghosh, Jason Li 等 2024-06-25T22:18:52Z 置信度 0.78 cs.SDcs.AIeess.AS
• Benchmarking XAI Explanations with Human-Aligned Evaluations
  We introduce PASTA (Perceptual Assessment System for explanaTion of Artificial Intelligence), a novel human-centric framework for evaluating eXplainable AI (XAI) techniques in computer vision. Our first contribution is the creation of the PASTA-dataset, the fi…
  arxiv Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier, Anna Hedström 等 2024-11-04T15:18:20Z 置信度 0.78 cs.CVcs.AIcs.HC
• Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation
  Large Language Models (LLMs) perform outstandingly in various downstream tasks, and the use of the Retrieval-Augmented Generation (RAG) architecture has been shown to improve performance for legal question answering (Nuruzzaman and Hussain, 2020; Louis et al.,…
  arxiv David Beauchemin, Zachary Gagnon, Ricahrd Khoury 2024-10-12T19:24:18Z 置信度 0.78 cs.CL
• General Vision Encoder Features as Guidance in Medical Image Registration
  General vision encoders like DINOv2 and SAM have recently transformed computer vision. Even though they are trained on natural images, such encoder models have excelled in medical imaging, e.g., in classification, segmentation, and registration. However, no in…
  arxiv Fryderyk Kögl, Anna Reithmeir, Vasiliki Sideri-Lampretsa, Ines Machado 等 2024-07-18T09:13:34Z 置信度 0.78 cs.CV
• Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection
  Compared to other clinical screening techniques, speech-and-language-based automated Alzheimer's disease (AD) detection methods are characterized by their non-invasiveness, cost-effectiveness, and convenience. Previous studies have demonstrated the efficacy of…
  arxiv Yin-Long Liu, Rui Feng, Jia-Hong Yuan, Zhen-Hua Ling 2024-12-09T07:18:29Z 置信度 0.78 eess.AScs.SD
• VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing
  Recent research on texture synthesis for 3D shapes benefits a lot from dramatically developed 2D text-to-image diffusion models, including inpainting-based and optimization-based approaches. However, these methods ignore the modal gap between the 2D diffusion …
  arxiv Shang Liu, Chaohui Yu, Chenjie Cao, Wen Qian 等 2024-07-05T12:11:33Z 置信度 0.78 cs.CV
• JaleesBench: Are AI Assistants Good Spiritual Company?
  Large language models are already advisors to millions of people of faith who bring them real decisions. The pressing question for a person of faith is not what a model knows or professes but what its counsel does to the person who receives it. We introduce Ja…
  arxiv M. Waleed Kadous, Benjamin Olsen 2026-06-27T11:59:43Z 置信度 0.78 cs.HCcs.AIcs.CL
• Echo: Learning from Experience Data via User-Driven Refinement
  Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend these barriers. Today…
  arxiv Hande Dong, Xiaoyun Liang, Jiarui Yu, Jiayi Lin 等 2026-05-21T04:34:00Z 置信度 0.78 cs.AIcs.CL
• Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias
  Collaborative Filtering (CF) typically suffers from the significant challenge of popularity bias due to the uneven distribution of items in real-world datasets. This bias leads to a significant accuracy gap between popular and unpopular items. It not only hind…
  arxiv Miaomiao Cai, Lei Chen, Yifan Wang, Haoyue Bai 等 2024-05-31T09:14:48Z 置信度 0.78 cs.IRcs.AI
• ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
  Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources. This enables LLMs to adapt to specific domains and mitigate hallucinations in knowledge-intensive tasks. However, existi…
  arxiv Lingxi Zhang, Yue Yu, Kuan Wang, Chao Zhang 2024-02-21T05:41:34Z 置信度 0.78 cs.CLcs.AIcs.IRcs.LG
• Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis
  Many visualizations have been developed for explainable AI (XAI), but they often require further reasoning by users to interpret. Investigating XAI for high-stakes medical diagnosis, we propose improving domain alignment with diagrammatic and abductive reasoni…
  arxiv Brian Y. Lim, Joseph P. Cahaly, Chester Y. F. Sng, Adam Chew 2023-02-02T17:23:28Z 置信度 0.78 cs.AIcs.HCcs.LG
• AI Feynman: a Physics-Inspired Method for Symbolic Regression
  A core challenge for both physics and artificial intellicence (AI) is symbolic regression: finding a symbolic expression that matches data from an unknown function. Although this problem is likely to be NP-hard in principle, functions of practical interest oft…
  arxiv Silviu-Marian Udrescu, Max Tegmark 2019-05-27T20:03:57Z 置信度 0.78 physics.comp-phcs.AIcs.LGhep-th
• Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
  How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, …
  arxiv Pedro R. A. S. Bassi, Wenxuan Li, Yucheng Tang, Fabian Isensee 等 2024-11-06T05:09:34Z 置信度 0.78 cs.CVcs.AI
• AI Needs Physics More Than Physics Needs AI
  Artificial intelligence (AI) is commonly depicted as transformative. Yet, after more than a decade of hype, its measurable impact remains modest outside a few high-profile scientific and commercial successes. The 2024 Nobel Prizes in Chemistry and Physics reco…
  arxiv Peter Coveney, Roger Highfield 2025-12-18T09:31:05Z 置信度 0.78 cs.AI
• Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
  In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs). We conduct a systematic empirical analysis of the harmlessness performance of representative MLLMs and reveal that the image input poses the alignment vulne…
  arxiv Yifan Li, Hangyu Guo, Kun Zhou, Wayne Xin Zhao 等 2024-03-14T18:24:55Z 置信度 0.78 cs.CVcs.CL
• Exact schedulability test for sporadic mixed-criticality real-time systems using antichains and oracles
  This work addresses the problem of exact schedulability assessment in uniprocessor mixed-criticality real-time systems with sporadic task sets. We model the problem by means of a finite automaton that has to be explored in order to check for schedulability. To…
  arxiv Simon Picard, Antonio Paolillo, Gilles Geeraerts, Joël Goossens 2024-10-23T22:35:55Z 置信度 0.78 cs.OS
• Introducing v0.5 of the AI Safety Benchmark from MLCommons
  This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a princ…
  arxiv Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed, Victor Akinwande 等 2024-04-18T15:01:00Z 置信度 0.78 cs.CLcs.AI
• Calibration Measurements of the BICEP3 and BICEP Array CMB Polarimeters from 2017 to 2024
  The BICEP3 and BICEP Array polarimeters are small-aperture refracting telescopes located at the South Pole designed to measure primordial gravitational wave signatures in the Cosmic Microwave Background (CMB) polarization, predicted by inflation. Constraining …
  arxiv Christos Giannakopoulos, Clara Vergès, P. A. R. Ade, Zeeshan Ahmed 等 2024-09-24T20:20:32Z 置信度 0.78 astro-ph.COastro-ph.IM
• BoilerTAI: A Platform for Enhancing Instruction Using Generative AI in Educational Forums
  Contribution: This Full paper in the Research Category track describes a practical, scalable platform that seamlessly integrates Generative AI (GenAI) with online educational forums, offering a novel approach to augment the instructional capabilities of staff.…
  arxiv Anvit Sinha, Shruti Goyal, Zachary Sy, Rhianna Kuperus 等 2024-09-20T04:00:30Z 置信度 0.78 cs.CYcs.HCcs.LG
• Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement
  Decompilation transforms compiled code back into a high-level programming language for analysis when source code is unavailable. Previous work has primarily focused on enhancing decompilation performance by increasing the scale of model parameters or training …
  arxiv Yunlong Feng, Dechuan Teng, Yang Xu, Honglin Mu 等 2024-06-25T02:37:53Z 置信度 0.78 cs.SEcs.CL
• Policy Fragmentation or Institutional Alignment? Institutional Governance of AI in Universities and Business Schools
  Artificial intelligence (AI) is rapidly transforming high-skilled domains, requiring higher education institutions (HEI) to balance the teaching of foundational principles with the integration of emerging tools to ensure workforce readiness. While HEI are incr…
  arxiv Lydia Manikonda, Dominique Outlaw 2026-08-04T12:39:33Z 置信度 0.78 cs.AIcs.CEcs.ET
• The BIRAFFE2 Experiment. Study in Bio-Reactions and Faces for Emotion-based Personalization for AI Systems
  The paper describes BIRAFFE2 data set, which is a result of an affective computing experiment conducted between 2019 and 2020, that aimed to develop computer models for classification and recognition of emotion. Such work is important to develop new methods of…
  arxiv Krzysztof Kutt, Dominika Drążyk, Maciej Szelążek, Szymon Bobek 等 2020-07-29T18:35:34Z 置信度 0.78 cs.HCcs.AIcs.LG
• Advancing Interactive Explainable AI via Belief Change Theory
  As AI models become ever more complex and intertwined in humans' daily lives, greater levels of interactivity of explainable AI (XAI) methods are needed. In this paper, we propose the use of belief change theory as a formal foundation for operators that model …
  arxiv Antonio Rago, Maria Vanina Martinez 2024-08-13T13:11:56Z 置信度 0.78 cs.AI
• KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge
  For Large Language Models (LLMs) to be effectively deployed in a specific country, they must possess an understanding of the nation's culture and basic knowledge. To this end, we introduce National Alignment, which measures an alignment between an LLM and a ta…
  arxiv Jiyoung Lee, Minwoo Kim, Seungho Kim, Junghwan Kim 等 2024-02-21T08:12:26Z 置信度 0.78 cs.CL
• Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
  In a realistic dialogue system, the input information from users is often subject to various types of input perturbations, which affects the slot-filling task. Although rule-based data augmentation methods have achieved satisfactory results, they fail to exhib…
  arxiv Jinxu Zhao, Guanting Dong, Yueyan Qiu, Tingfeng Hui 等 2024-02-22T12:39:50Z 置信度 0.78 cs.CL
• Unification of Balti and trans-border sister dialects in the essence of LLMs and AI Technology
  The language called Balti belongs to the Sino-Tibetan, specifically the Tibeto-Burman language family. It is understood with variations, across populations in India, China, Pakistan, Nepal, Tibet, Burma, and Bhutan, influenced by local cultures and producing v…
  arxiv Muhammad Sharif, Jiangyan Yi, Muhammad Shoaib 2024-11-20T15:48:21Z 置信度 0.78 cs.CLcs.AIcs.CV
• Assurance of AI Systems From a Dependability Perspective
  We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key element in this "depe…
  arxiv Robin Bloomfield, John Rushby 2024-07-18T23:55:43Z 置信度 0.78 cs.AI
• Aligned: A Platform-based Process for Alignment
  We are introducing Aligned, a platform for global governance and alignment of frontier models, and eventually superintelligence. While previous efforts at the major AI labs have attempted to gather inputs for alignment, these are often conducted behind closed …
  arxiv Ethan Shaotran, Ido Pesok, Sam Jones, Emi Liu 2023-11-15T05:12:37Z 置信度 0.78 cs.CYcs.AI
• Aligning XAI with EU Regulations for Smart Biomedical Devices: A Methodology for Compliance Analysis
  Significant investment and development have gone into integrating Artificial Intelligence (AI) in medical and healthcare applications, leading to advanced control systems in medical technology. However, the opacity of AI systems raises concerns about essential…
  arxiv Francesco Sovrano, Michael Lognoul, Giulia Vilone 2024-08-27T14:59:27Z 置信度 0.78 cs.AIcs.CY
• Leveraging small language models for Text2SPARQL tasks to improve the resilience of AI assistance
  In this work we will show that language models with less than one billion parameters can be used to translate natural language to SPARQL queries after fine-tuning. Using three different datasets ranging from academic to real world, we identify prerequisites th…
  arxiv Felix Brei, Johannes Frey, Lars-Peter Meyer 2024-05-27T11:47:21Z 置信度 0.78 cs.AIcs.CLcs.IR
• Evolution of SAE Features Across Layers in LLMs
  Sparse Autoencoders for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjacent layers to understand how features evolve through a forward pass. We provide …
  arxiv Daniel Balcells, Benjamin Lerner, Michael Oesterle, Ediz Ucar 等 2024-10-11T14:46:49Z 置信度 0.78 cs.LG
• Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiology
  Recent advances in AI combine large language models (LLMs) with vision encoders that bring forward unprecedented technical capabilities to leverage for a wide range of healthcare applications. Focusing on the domain of radiology, vision-language models (VLMs) …
  arxiv Nur Yildirim, Hannah Richardson, Maria T. Wetscherek, Junaid Bajwa 等 2024-02-22T03:32:17Z 置信度 0.78 cs.HC
• Automated Meta Prompt Engineering for Alignment with the Theory of Mind
  We introduce a method of meta-prompting that jointly produces fluent text for complex tasks while optimizing the similarity of neural states between a human's mental expectation and a Large Language Model's (LLM) neural processing. A technique of agentic reinf…
  arxiv Aaron Baughman, Rahul Agarwal, Eduardo Morales, Gozde Akay 2025-05-13T23:42:36Z 置信度 0.78 cs.AIcs.CLcs.LG
• A Taxonomy of Collectible Card Games from a Game-Playing AI Perspective
  Collectible card games are challenging, widely played games that have received increasing attention from the AI research community in recent years. Despite important breakthroughs, the field still poses many unresolved challenges. This work aims to help furthe…
  arxiv Ronaldo e Silva Vieira, Anderson Rocha Tavares, Luiz Chaimowicz 2024-10-08T19:04:12Z 置信度 0.78 cs.AI
• Antagonistic AI
  The vast majority of discourse around AI development assumes that subservient, "moral" models aligned with "human values" are universally beneficial -- in short, that good AI is sycophantic AI. We explore the shadow of the sycophantic paradigm, a design space …
  arxiv Alice Cai, Ian Arawjo, Elena L. Glassman 2024-02-12T00:44:37Z 置信度 0.78 cs.AIcs.HC
• Distrust in (X)AI -- Measurement Artifact or Distinct Construct?
  Trust is a key motivation in developing explainable artificial intelligence (XAI). However, researchers attempting to measure trust in AI face numerous challenges, such as different trust conceptualizations, simplified experimental tasks that may not induce un…
  arxiv Nicolas Scharowski, Sebastian A. C. Perrig 2023-03-29T07:14:54Z 置信度 0.78 cs.HCcs.AI
• Open Mathematical Tasks as a Didactic Response to Generative Artificial Intelligence in Post-AI Contexts
  The widespread availability of generative artificial intelligence tools poses new challenges for school mathematics education, particularly regarding the formative role of traditional mathematical tasks. In post-AI educational contexts, many activities can be …
  arxiv Felix De la Cruz Serrano 2026-02-09T22:16:04Z 置信度 0.78 math.HOcs.CY
• Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study
  Dilated Convolution with Learnable Spacing (DCLS) is a recent advanced convolution method that allows enlarging the receptive fields (RF) without increasing the number of parameters, like the dilated convolution, yet without imposing a regular grid. DCLS has b…
  arxiv Rabih Chamas, Ismail Khalfaoui-Hassani, Timothee Masquelier 2024-08-06T13:05:32Z 置信度 0.78 cs.CVcs.AI
• Getting Ready for the EU AI Act in Healthcare. A call for Sustainable AI Development and Deployment
  Assessments of trustworthiness have become a cornerstone of responsible AI development. Especially in high-stakes fields like healthcare, aligning technical, evidence-based, and ethical practices with forthcoming legal requirements is increasingly urgent. We a…
  arxiv John Brandt Brodersen, Ilaria Amelia Caggiano, Pedro Kringen, Vince Istvan Madai 等 2025-05-10T07:46:54Z 置信度 0.78 cs.CYcs.AI
• Rethinking AI Evaluation in Education: The TEACH-AI Framework and Benchmark for Generative AI Assistants
  As generative artificial intelligence (AI) continues to transform education, most existing AI evaluations rely primarily on technical performance metrics such as accuracy or task efficiency while overlooking human identity, learner agency, contextual learning …
  arxiv Shi Ding, Brian Magerko 2025-11-28T17:42:36Z 置信度 0.78 cs.CYcs.AIcs.HCcs.LG
• Misalignment or misuse? The AGI alignment tradeoff
  Creating systems that are aligned with our goals is seen as a leading approach to create safe and beneficial AI in both leading AI companies and the academic field of AI safety. We defend the view that misaligned AGI - future, generally intelligent (robotic) A…
  arxiv Max Hellrigel-Holderbaum, Leonard Dung 2025-06-04T09:22:37Z 置信度 0.78 cs.CYcs.AI
• Semantic Alignment for Multimodal Large Language Models
  Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g., change captioning). Exis…
  arxiv Tao Wu, Mengze Li, Jingyuan Chen, Wei Ji 等 2024-08-23T06:48:46Z 置信度 0.78 cs.CV
• Towards Multi-dimensional Explanation Alignment for Medical Classification
  The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several challenges, including dependency on specific models, difficulties in understandi…
  arxiv Lijie Hu, Songning Lai, Wenshuo Chen, Hongru Xiao 等 2024-10-28T20:03:19Z 置信度 0.78 cs.CVcs.AIcs.LG
• On Augmenting Scenario-Based Modeling with Generative AI
  The manual modeling of complex systems is a daunting task; and although a plethora of methods exist that mitigate this issue, the problem remains very difficult. Recent advances in generative AI have allowed the creation of general-purpose chatbots, capable of…
  arxiv David Harel, Guy Katz, Assaf Marron, Smadar Szekely 2024-01-04T12:58:25Z 置信度 0.78 cs.SE
• Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark
  RGB and Thermal (RGBT) Salient Object Detection (SOD) aims to achieve high-quality saliency prediction by exploiting the complementary information of visible and thermal image pairs, which are initially captured in an unaligned manner. However, existing method…
  arxiv Kunpeng Wang, Danying Lin, Chenglong Li, Zhengzheng Tu 等 2024-06-03T01:01:58Z 置信度 0.78 cs.CV
• SEME at SemEval-2024 Task 2: Comparing Masked and Generative Language Models on Natural Language Inference for Clinical Trials
  This paper describes our submission to Task 2 of SemEval-2024: Safe Biomedical Natural Language Inference for Clinical Trials. The Multi-evidence Natural Language Inference for Clinical Trial Data (NLI4CT) consists of a Textual Entailment (TE) task focused on …
  arxiv Mathilde Aguiar, Pierre Zweigenbaum, Nona Naderi 2024-04-05T09:18:50Z 置信度 0.78 cs.CL
• CodecLM: Aligning Language Models with Tailored Synthetic Data
  Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor and time cost to col…
  arxiv Zifeng Wang, Chun-Liang Li, Vincent Perot, Long T. Le 等 2024-04-08T21:15:36Z 置信度 0.78 cs.CLcs.AIcs.LG
• 1st Place Winner of the 2024 Pixel-level Video Understanding in the Wild (CVPR'24 PVUW) Challenge in Video Panoptic Segmentation and Best Long Video Consistency of Video Semantic Segmentation
  The third Pixel-level Video Understanding in the Wild (PVUW CVPR 2024) challenge aims to advance the state of art in video understanding through benchmarking Video Panoptic Segmentation (VPS) and Video Semantic Segmentation (VSS) on challenging videos and scen…
  arxiv Qingfeng Liu, Mostafa El-Khamy, Kee-Bong Song 2024-06-08T04:43:08Z 置信度 0.78 cs.CV
• FirstPass: Grounding AI Scientific Judgment in Multi-Round Editorial Outcomes
  AI systems for peer review fail on three fronts: they train on Computer Science and Machine Learning venues alone, ignore the iterative dialogue that validates science, and evaluate on stylistic mimicry rather than real editorial judgment. We introduce FirstPa…
  arxiv Prabhjot Singh, Somnath Luitel, Manmeet Singh, Josh Durkee 2026-06-18T15:06:36Z 置信度 0.78 cs.CLcs.AIcs.LG
• Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection
  The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video…
  arxiv Yang Liu, Tongfei Shen, Dong Zhang, Qingying Sun 等 2024-02-14T10:05:19Z 置信度 0.78 cs.CVcs.AI
• Artificial Intelligence in Financial Forecasting: Analyzing the Suitability of AI Models for Dollar/TL Exchange Rate Predictions
  The development of artificial intelligence has made significant contributions to the financial sector. One of the main interests of investors is price predictions. Technical and fundamental analyses, as well as econometric analyses, are conducted for price pre…
  arxiv Asef Yelghi, Aref Yelghi, Shirmohammad Tavangari 2024-11-06T21:05:10Z 置信度 0.78 econ.GN
• Discovery of Feasible 3D Printing Configurations for Metal Alloys via AI-driven Adaptive Experimental Design
  Configuring the parameters of additive manufacturing processes for metal alloys is a challenging problem due to complex relationships between input parameters (e.g., laser power, scan speed) and quality of printed outputs. The standard trial-and-error approach…
  arxiv Azza Fadhel, Nathaniel W. Zuckschwerdt, Aryan Deshwal, Susmita Bose 等 2026-01-24T20:57:27Z 置信度 0.78 cs.AIcs.LG
• Uncovering AI Governance Themes in EU Policies using BERTopic and Thematic Analysis
  The upsurge of policies and guidelines that aim to ensure Artificial Intelligence (AI) systems are safe and trustworthy has led to a fragmented landscape of AI governance. The European Union (EU) is a key actor in the development of such policies and guideline…
  arxiv Delaram Golpayegani, Marta Lasek-Markey, Arjumand Younus, Aphra Kerr 等 2025-09-16T12:20:07Z 置信度 0.78 cs.CYcs.AI
• PromptMind Team at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles
  This paper describes our approach to the MEDIQA-CORR shared task, which involves error detection and correction in clinical notes curated by medical professionals. This task involves handling three subtasks: detecting the presence of errors, identifying the sp…
  arxiv Satya Kesav Gundabathula, Sriram R Kolar 2024-05-14T07:16:36Z 置信度 0.78 cs.CLcs.AIcs.LG
• Learning with Alignments: Tackling the Inter- and Intra-domain Shifts for Cross-multidomain Facial Expression Recognition
  Facial Expression Recognition (FER) holds significant importance in human-computer interactions. Existing cross-domain FER methods often transfer knowledge solely from a single labeled source domain to an unlabeled target domain, neglecting the comprehensive i…
  arxiv Yuxiang Yang, Lu Wen, Xinyi Zeng, Yuanyuan Xu 等 2024-07-08T07:43:06Z 置信度 0.78 cs.CVcs.AI
• Inference Optimization of Foundation Models on AI Accelerators
  Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry and research community have witnessed a large number of new applications, based on…
  arxiv Youngsuk Park, Kailash Budhathoki, Liangfu Chen, Jonas Kübler 等 2024-07-12T09:24:34Z 置信度 0.78 cs.AIcs.LG
• The Alignment Problem in Context
  A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to hypothetical future A…
  arxiv Raphaël Millière 2023-11-03T17:57:55Z 置信度 0.78 cs.LGcs.AI
• Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection
  Multimodal hateful content detection is a challenging task that requires complex reasoning across visual and textual modalities. Therefore, creating a meaningful multimodal representation that effectively captures the interplay between visual and textual featu…
  arxiv Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque, Sarah M. Preum 2024-02-15T06:34:15Z 置信度 0.78 cs.CL
• Annotation alignment: Comparing LLM and human annotations of conversational safety
  Do LLMs align with human perceptions of safety? We study this question via annotation alignment, the extent to which LLMs and humans agree when annotating the safety of user-chatbot conversations. We leverage the recent DICES dataset (Aroyo et al., 2023), in w…
  arxiv Rajiv Movva, Pang Wei Koh, Emma Pierson 2024-06-10T15:30:13Z 置信度 0.78 cs.CL
• Efficient Parameter Optimisation for Quantum Kernel Alignment: A Sub-sampling Approach in Variational Training
  Quantum machine learning with quantum kernels for classification problems is a growing area of research. Recently, quantum kernel alignment techniques that parameterise the kernel have been developed, allowing the kernel to be trained and therefore aligned wit…
  arxiv M. Emre Sahin, Benjamin C. B. Symons, Pushpak Pati, Fayyaz Minhas 等 2024-01-05T16:11:34Z 置信度 0.78 quant-phcs.LG
• Near-infrared spectroscopy of the LMC recurrent nova LMCN 1968-12a
  We have obtained near-infrared ($0.80-2.45μ$m) spectra of the recurrent nova LMCN 1968-12a on two occasions during its 2024 August eruption. This is the first near-infrared spectroscopy of an extragalactic nova. The initial spectrum, on day 8.48, caught the no…
  arxiv A. Evans, D. P. K. Banerjee, T. R. Geballe, A. Polin 等 2024-12-05T14:49:09Z 置信度 0.78 astro-ph.SRastro-ph.GA
• Learning Modality Knowledge Alignment for Cross-Modality Transfer
  Cross-modality transfer aims to leverage large pretrained models to complete tasks that may not belong to the modality of pretraining data. Existing works achieve certain success in extending classical finetuning to cross-modal scenarios, yet we still lack und…
  arxiv Wenxuan Ma, Shuang Li, Lincan Cai, Jingxuan Kang 2024-06-27T03:23:47Z 置信度 0.78 cs.CV
• Steps Towards Value-Aligned Systems
  Algorithmic (including AI/ML) decision-making artifacts are an established and growing part of our decision-making ecosystem. They are indispensable tools for managing the flood of information needed to make effective decisions in a complex world. The current …
  arxiv Osonde A. Osoba, Benjamin Boudreaux, Douglas Yeung 2020-02-10T22:47:30Z 置信度 0.78 cs.CY
• Beyond Labels: Aligning Large Language Models with Human-like Reasoning
  Aligning large language models (LLMs) with a human reasoning approach ensures that LLMs produce morally correct and human-like decisions. Ethical concerns are raised because current models are prone to generating false positives and providing malicious respons…
  arxiv Muhammad Rafsan Kabir, Rafeed Mohammad Sultan, Ihsanul Haque Asif, Jawad Ibn Ahad 等 2024-08-20T17:44:51Z 置信度 0.78 cs.CLcs.AIcs.LG
• Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles
  AI agents that communicate on behalf of individuals need to capture how each person actually communicates, yet current approaches either require costly per-person fine-tuning, produce generic outputs from shallow persona descriptions, or optimize preferences w…
  arxiv Ruoxi Shang, Dan Marshall, Edward Cutrell, Denae Ford 2026-03-27T18:55:44Z 置信度 0.78 cs.HCcs.AI
• Speaker- and Text-Independent Estimation of Articulatory Movements and Phoneme Alignments from Speech
  This paper introduces a novel combination of two tasks, previously treated separately: acoustic-to-articulatory speech inversion (AAI) and phoneme-to-articulatory (PTA) motion estimation. We refer to this joint task as acoustic phoneme-to-articulatory speech i…
  arxiv Tobias Weise, Philipp Klumpp, Kubilay Can Demir, Paula Andrea Pérez-Toro 等 2024-07-03T14:13:04Z 置信度 0.78 cs.SDcs.AIcs.CLcs.LGeess.AS
• Strategies for Increasing Corporate Responsible AI Prioritization
  Responsible artificial intelligence (RAI) is increasingly recognized as a critical concern. However, the level of corporate RAI prioritization has not kept pace. In this work, we conduct 16 semi-structured interviews with practitioners to investigate what has …
  arxiv Angelina Wang, Teresa Datta, John P. Dickerson 2024-05-06T21:04:06Z 置信度 0.78 cs.CY
• Generative AI for Social Impact
  AI for Social Impact (AI4SI) has achieved compelling results in public health, conservation, and security, yet scaling these successes remains difficult due to a persistent deployment bottleneck. We characterize this bottleneck through three coupled gaps: obse…
  arxiv Lingkai Kong, Cheol Woo Kim, Davin Choo, Milind Tambe 2026-01-05T02:44:39Z 置信度 0.78 cs.CY
• AI chatbots versus human healthcare professionals: a systematic review and meta-analysis of empathy in patient care
  Background: Empathy is widely recognized for improving patient outcomes, including reduced pain and anxiety and improved satisfaction, and its absence can cause harm. Meanwhile, use of artificial intelligence (AI)-based chatbots in healthcare is rapidly expand…
  arxiv Alastair Howcroft, Amber Bennett-Weston, Ahmad Khan, Joseff Griffiths 等 2026-02-05T13:09:19Z 置信度 0.78 cs.HCcs.AIcs.CL
• AEMA: Verifiable Evaluation Framework for Trustworthy and Controlled Agentic LLM Systems
  Evaluating large language model (LLM)-based multi-agent systems remains a critical challenge, as these systems must exhibit reliable coordination, transparent decision-making, and verifiable performance across evolving tasks. Existing evaluation approaches oft…
  arxiv YenTing Lee, Keerthi Koneru, Zahra Moslemi, Sheethal Kumar 等 2026-01-17T04:09:02Z 置信度 0.78 cs.AI
• Confronting the Reproducibility Crisis: A Case Study of Challenges in Cybersecurity AI
  In the rapidly evolving field of cybersecurity, ensuring the reproducibility of AI-driven research is critical to maintaining the reliability and integrity of security systems. This paper addresses the reproducibility crisis within the domain of adversarial ro…
  arxiv Richard H. Moulton, Gary A. McCully, John D. Hastings 2024-05-29T04:37:19Z 置信度 0.78 cs.LGcs.AIcs.CR
• Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts
  Generative AI has the potential to create a new form of interactive media: AI-bridged creative language arts (CLA), which bridge the author and audience by personalizing the author's vision to the audience's context and taste at scale. However, it is unclear w…
  arxiv Taewook Kim, Hyomin Han, Eytan Adar, Matthew Kay 等 2024-03-01T10:53:10Z 置信度 0.78 cs.HCcs.AI
• Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)
  This position paper argues that formal optimal control theory should be central to AI alignment research, offering a distinct perspective from prevailing AI safety and security approaches. While recent work in AI safety and mechanistic interpretability has adv…
  arxiv Elija Perrier 2025-06-21T22:45:19Z 置信度 0.78 cs.AI
• Shapley Value-based Contrastive Alignment for Multimodal Information Extraction
  The rise of social media and the exponential growth of multimodal communication necessitates advanced techniques for Multimodal Information Extraction (MIE). However, existing methodologies primarily rely on direct Image-Text interactions, a paradigm that ofte…
  arxiv Wen Luo, Yu Xia, Shen Tianshu, Sujian Li 2024-07-25T08:15:43Z 置信度 0.78 cs.AIcs.CLcs.MM
• EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
  In this report, we present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge. Building upon the video-language two-tower model and leveraging our meticulously organ…
  arxiv Baoqi Pei, Guo Chen, Jilan Xu, Yuping He 等 2024-06-26T05:01:37Z 置信度 0.78 cs.CV
• How Could Generative AI Support Compliance with the EU AI Act? A Review for Safe Automated Driving Perception
  Deep Neural Networks (DNNs) have become central for the perception functions of autonomous vehicles, substantially enhancing their ability to understand and interpret the environment. However, these systems exhibit inherent limitations such as brittleness, opa…
  arxiv Mert Keser, Youssef Shoeb, Alois Knoll 2024-08-30T12:01:06Z 置信度 0.78 cs.CV
• Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety
  Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks. We extend it to open-ended clinical conversation under missing information, where safe behavior means recognizing absent information and qualifying, clarifying, or no…
  arxiv Koyar Afrasyab 2026-07-21T08:05:35Z 置信度 0.78 cs.AI
• MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers
  Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in parameter-efficient audi…
  arxiv Tanvir Mahmud, Shentong Mo, Yapeng Tian, Diana Marculescu 2024-06-07T13:35:44Z 置信度 0.78 cs.CVcs.MMcs.SDeess.AS
• Why AI Readiness Is an Organizational Learning Problem, Not a Technology Purchase
  Global corporate AI investment reached $252.3 billion in 2024, yet only 6% of firms report significant earnings impact. This article argues that AI project failure is fundamentally an organizational learning problem rather than a technology deficit. Drawing on…
  arxiv Jeanne McClure, Gregg Gerdau 2026-03-22T22:30:05Z 置信度 0.78 cs.CYcs.AIcs.CL
• Finding longer cycles via shortest colourful cycle
  We consider the parameterised $k,e$-Long Cycle problem, in which you are given an $n$-vertex undirected graph $G$, a specified edge $e$ in $G$, and a positive integer $k$, and are asked to decide if the graph $G$ has a simple cycle through $e$ of length at lea…
  arxiv Andreas Björklund, Thore Husfeldt 2024-08-07T11:28:55Z 置信度 0.78 cs.DS
• The UK Submillimetre and Millimetre Astronomy Roadmap 2024
  In this Roadmap, we present a vision for the future of submillimetre and millimetre astronomy in the United Kingdom over the next decade and beyond. This Roadmap has been developed in response to the recommendation of the Astronomy Advisory Panel (AAP) of the …
  arxiv K. Pattle, P. S. Barry, A. W. Blain, M. Booth 等 2024-08-23T10:48:38Z 置信度 0.78 astro-ph.IM
• The Mechanical Turkness: Tactical Media Art and the Critique of Corporate AI
  The extensive industrialization of artificial intelligence (AI) since the mid-2010s has increasingly motivated artists to address its economic and sociopolitical consequences. In this chapter, I discuss interrelated art practices that thematize creative agency…
  arxiv Dejan Grba 2024-02-27T13:16:50Z 置信度 0.78 cs.CYcs.AI
• The CASTLE 2024 Dataset: Advancing the Art of Multimodal Understanding
  Egocentric video has seen increased interest in recent years, as it is used in a range of areas. However, most existing datasets are limited to a single perspective. In this paper, we present the CASTLE 2024 dataset, a multimodal collection containing ego- and…
  arxiv Luca Rossetto, Werner Bailer, Duc-Tien Dang-Nguyen, Graham Healy 等 2025-03-21T13:01:07Z 置信度 0.78 cs.MMcs.AIcs.CVcs.IR
• MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness
  This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual. The task aims to detect semantic relatedness of two sentences in a given target language without access to direct supervision (…
  arxiv Shijia Zhou, Huangyan Shan, Barbara Plank, Robert Litschko 2024-04-03T08:44:51Z 置信度 0.78 cs.CL
• Management Respond to Negative Feedback: AI-Powered Insights for Effective Engagement
  The reputation of a business is significantly influenced by online reviews, with negative feedback having the potential to harm a brand's image and dissuade potential customers. To safeguard their image and convert dissatisfied users into loyal ones, businesse…
  openalex Aytac Gokce, Mina Tajvidi, Nick Hajli 2024-01-01 置信度 0.72 ReputationHarmLoyaltyPhoneLoyalty program
• Biomolecular Interaction Prediction: The Era of AI
  Predicting biomolecular interactions is a crucial task in drug discovery and molecular biology. Deep learning, with its ability to learn complex patterns from large datasets, has shown promising results in predicting biomolecular interactions. In this review, …
  openalex Haoping Wang, Xiangjie Meng, Yang Zhang 2025-07-16 置信度 0.72 Deep learningComputer scienceDrug discoveryArtificial intelligenceMachine learning
• Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
  Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free. Novel applications …
  openalex Shusheng Xu, Wei Fu, Jiaxuan Gao, Wenjie Ye 等 2024-04-16 置信度 0.72 Natural language processingComputer science
• Generative AI as a “placement buddy”: Supporting pre-service teachers in work-integrated learning, self-management and crisis resolution
  This study explored the integration of generative artificial intelligence (GenAI) in supporting pre-service teachers (PSTs) during their work-integrated learning placements, focusing on its role in lesson planning, teaching and WIL crisis resolution. Using the…
  openalex Walter Barbieri, Ngoc Nhu Nguyen 2025-04-24 置信度 0.72 Generative grammarComputer scienceSelf-serviceService (business)Resolution (logic)
• Fragments of the past: The intersection of AI, historical imagery, and early childhood creativity
  Abstract This paper explores the intersection of early childhood education and AI, with a focus on promoting multimodal play. Drawing from implementation research in preschools, we explore the potential of an AI‐powered painting tool to foster historical image…
  openalex Ilene R. Berson, Michael J. Berson 2024-08-14 置信度 0.72 CreativityIntersection (aeronautics)PsychologyHistoryCognitive psychology