点击阅读原文访问arxivdaily.com，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏等功能！
cs.LG 方向，今日共计129篇
大模型相关(18篇)
【1】Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving
标题：驾驶我的方式：个性化驾驶的视觉-语言-动作模型的偏好一致
链接：https://arxiv.org/abs/2603.25740
作者：Zehao Wang, Huaide Jiang, Shuaiwu Dong, Yuping Wang, Hang Qiu, Jiachen Li
备注：IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026); Project website: this https URL
摘要：
摘要：
【2】Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers
标题：超越Via：学术论文中大型语言模型影响的分析与评估
链接：https://arxiv.org/abs/2603.25638
作者：Mingmeng Geng, Yuhang Dong, Thierry Poibeau
备注：Visualization of word usage patterns in arXiv abstracts: this https URL
摘要：
摘要：
【3】Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models
标题：形状与实质：对局部视觉语言模型的双层侧信道攻击
链接：https://arxiv.org/abs/2603.25403
作者：Eyal Hadad, Mordechai Guri
备注：13 pages, 8 figures
摘要：
摘要：
【4】GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs
标题：GlowQ：量化LLM的群共享低秩近似
链接：https://arxiv.org/abs/2603.25385
作者：Selim An, Il hong Suh, Yeseong Kim
摘要：
摘要：
【5】How Pruning Reshapes Features: Sparse Autoencoder Analysis of Weight-Pruned Language Models
标题：修剪如何重塑特征：权重修剪语言模型的稀疏自动编码器分析
链接：https://arxiv.org/abs/2603.25325
作者：Hector Borobia, Elies Seguí-Mas, Guillermina Tormo-Carbó
备注：27 pages, 6 figures, 6 tables. Analysis covers Gemma 3 1B, Gemma 2 2B, and Llama 3.2 1B across 22 experimental runs. Code and data available at this https URL
摘要：
摘要：
【6】Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models
标题：激活问题：视觉语言模型用于OOD检测的测试时激活阴性标签
链接：https://arxiv.org/abs/2603.25250
作者：Yabin Zhang, Maya Varma, Yunhe Gao, Jean-Benoit Delbrouck, Jiaming Liu, Chong Wang, Curtis Langlotz
备注：CVPR 2026 main track, Codes are available at this https URL
摘要：
摘要：
【7】SIGMA: Structure-Invariant Generative Molecular Alignment for Chemical Language Models via Autoregressive Contrastive Learning
标题：SIGMA：通过自回归对比学习实现化学语言模型的结构不变生成分子对齐
链接：https://arxiv.org/abs/2603.25062
作者：Xinyu Wang, Fei Dou, Jinbo Bi, Minghu Song
备注：15 pages, 6 figures. Submitted to ICML 2026. Primary category: cs.LG (Machine Learning); Secondary: cs.AI, q-bio.QM
摘要：
摘要：
【8】MobileDev-Bench: A Comprehensive Benchmark for Evaluating Language Models on Mobile Application Development
标题：MobileDev-Bench：一个评估移动应用开发语言模型的综合基准
链接：https://arxiv.org/abs/2603.24946
作者：Moshood A. Fakorede, Krishna Upadhyay, A.B. Siddique, Umar Farooq
备注：21 pages, 11 figures, 14 tables
摘要：
摘要：
【9】Estimating near-verbatim extraction risk in language models with decoding-constrained beam search
标题：使用解码约束的束搜索估计语言模型中的近逐字提取风险
链接：https://arxiv.org/abs/2603.24917
作者：A. Feder Cooper, Mark A. Lemley, Christopher De Sa, Lea Duesterwald, Allison Casasola, Jamie Hayes, Katherine Lee, Daniel E. Ho, Percy Liang
摘要：
摘要：
【10】Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization
标题：员工学习：用于仓库人员配置优化的离线强化学习和精调LLM
链接：https://arxiv.org/abs/2603.24883
作者：Kalle Kujanpää, Yuying Zhu, Kristina Klinkner, Shervin Malmasi
备注：ICLR 2026 Workshop on AI for Mechanism Design and Strategic Decision Making
摘要：
摘要：
【11】NeuroVLM-Bench: Evaluation of Vision-Enabled Large Language Models for Clinical Reasoning in Neurological Disorders
标题：NeuroVLM-Bench：用于神经系统疾病临床推理的视觉支持大型语言模型的评估
链接：https://arxiv.org/abs/2603.24846
作者：Katarina Trojachanec Dineva, Stefan Andonov, Ilinka Ivanoska, Ivan Kitanovski, Sasho Gramatikov, Tamara Kostova, Monika Simjanoska Misheva, Kostadin Mishev
备注：53 pages, 12 figures. Manuscript submitted to the BMC Medical Informatics and Decision Making journal
摘要：
摘要：
【12】Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
标题：超越模式：语言模型中的分布式推理RL
链接：https://arxiv.org/abs/2603.24844
作者：Isha Puri, Mehul Damani, Idan Shenfeld, Marzyeh Ghassemi, Jacob Andreas, Yoon Kim
摘要：
摘要：
【13】Evaluating Fine-Tuned LLM Model For Medical Transcription With Small Low-Resource Languages Validated Dataset
标题：使用小型低资源语言验证数据集评估用于医学转录的精调LLM模型
链接：https://arxiv.org/abs/2603.24772
作者：Mohammed Nowshad Ruhani Chowdhury, Mohammed Nowaz Rabbani Chowdhury, Sakari Lukkarinen
备注：9 pages, 3 figures, 2 tables
摘要：
摘要：
【14】Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models
标题：可扩展对象关系编码，在大型语言模型中实现更好的3D空间推理
链接：https://arxiv.org/abs/2603.24721
作者：Shengli Zhou, Minghang Zheng, Feng Zheng, Yang Liu
备注：Accepted by CVPR 2026
摘要：
摘要：
【15】Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards
标题：通过约束数据合成和毕业奖励训练LLM进行多步骤刀具规划
链接：https://arxiv.org/abs/2603.24709
作者：Cheng Jiayang, Xin Liu, Zhihan Zhang, Haoyang Wen, Zixuan Zhang, Qingyu Yin, Shiyang Li, Priyanka Nigam, Bing Yin, Chao Zhang, Yangqiu Song
备注：Under Review
摘要：
摘要：
【16】Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch
标题：LLM能否击败经典超参数优化算法？自我研究研究
链接：https://arxiv.org/abs/2603.24647
作者：Fabio Ferreira, Lucca Wobbe, Arjun Krishnakumar, Frank Hutter, Arber Zela
摘要：
摘要：
【17】Experiential Reflective Learning for Self-Improving LLM Agents
标题：自我提升的LLM代理人的体验式反思学习
链接：https://arxiv.org/abs/2603.24639
作者：Marc-Antoine Allard, Arnaud Teinturier, Victor Xing, Gautier Viaud
备注：Published as a conference paper at the ICLR 2026 MemAgents Workshop
摘要：
摘要：
【18】Multi-LLM Query Optimization
标题：多LLM查询优化
链接：https://arxiv.org/abs/2603.24617
作者：Arlen Dean, Zijin Zhang, Stefanus Jasin, Yuqing Liu
摘要：
摘要：
Graph相关(图学习|图神经网络|图优化等)(4篇)
【1】GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
标题：GraphER：一种高效的基于图的丰富和重新排序方法，用于检索增强生成
链接：https://arxiv.org/abs/2603.24925
作者：Ruizhong Miao, Yuying Wang, Rongguang Wang, Chenyang Li, Tao Sheng, Sujith Ravi, Dan Roth
摘要：
摘要：
【2】Learning Mesh-Free Discrete Differential Operators with Self-Supervised Graph Neural Networks
标题：用自监督图神经网络学习无网格离散微运算符
链接：https://arxiv.org/abs/2603.24641
作者：Lucas Gerken Starepravo, Georgios Fourtakas, Steven Lind, Ajay B. Harish, Tianning Tang, Jack R. C. King
摘要：
摘要：
【3】DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph
标题：DyMRL：知识图中用于多模式事件预测的动态多空间表示学习
链接：https://arxiv.org/abs/2603.24636
作者：Feng Zhao, Kangzheng Liu, Teng Peng, Yu Yang, Guandong Xu
备注：Accepted to The ACM Web Conference 2026 (WWW '26). This version is published under a CC BY license
摘要：
摘要：
【4】Dual-Graph Multi-Agent Reinforcement Learning for Handover Optimization
标题：用于切换优化的双图多智能体强化学习
链接：https://arxiv.org/abs/2603.24634
作者：Matteo Salvatori, Filippo Vannella, Sebastian Macaluso, Stylianos E. Trevlakis, Carlos Segura Perales, José Suarez-Varela, Alexandros-Apostolos A. Boulogeorgos, Ioannis Arapakis
摘要：
摘要：
Transformer(4篇)
【1】Anchored-Branched Steady-state WInd Flow Transformer (AB-SWIFT): a metamodel for 3D atmospheric flow in urban environments
标题：锚定分支稳态WInd流量Transformer（AB-SWIFT）：城市环境中3D大气流的元模型
链接：https://arxiv.org/abs/2603.25635
作者：Armand de Villeroché, Rem-Sophia Mouradi, Vincent Le Guen, Sibo Cheng, Marc Bocquet, Alban Farchi, Patrick Armand, Patrick Massin
摘要：
摘要：
【2】Offline Decision Transformers for Neural Combinatorial Optimization: Surpassing Heuristics on the Traveling Salesman Problem
标题：神经组合优化的离线决策转换器：旅行推销员问题的超越启发式
链接：https://arxiv.org/abs/2603.25241
作者：Hironori Ohigashi, Shinichiro Hamada
备注：11 pages, 1 figures. Accepted at NeurIPS 2025 Workshop on DiffCoALG
摘要：
摘要：
【3】Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
标题：黑暗中的Transformer：通过强盗反馈导航未知的搜索空间
链接：https://arxiv.org/abs/2603.24780
作者：Jungtaek Kim, Thomas Zeng, Ziqian Lin, Minjae Lee, Chungpa Lee, Jy-yong Sohn, Hyung Il Koo, Kangwook Lee
备注：Accepted for publication in Transactions on Machine Learning Research (TMLR)
摘要：
摘要：
【4】FED-HARGPT: A Hybrid Centralized-Federated Approach of a Transformer-based Architecture for Human Context Recognition
标题：FED-HARGPT：一种基于转换器架构的混合集中式联邦方法，用于人类上下文识别
链接：https://arxiv.org/abs/2603.24601
作者：Wandemberg Gibaut, Alexandre Osorio, Amparo Munoz, Sildolfo F. G. Neto, Fabio Grassiotto
备注：Paper presented on: July 2025 Conference: XVII Simpósio Brasileiro de Automação Inteligente (SBAI) At: São João del-Rei
摘要：
摘要：
GAN|对抗|攻击|生成相关(4篇)
【1】Mitigating Evasion Attacks in Fog Computing Resource Provisioning Through Proactive Hardening
标题：通过主动硬化缓解雾计算资源配置中的逃避攻击
链接：https://arxiv.org/abs/2603.25257
作者：Younes Salmi, Hanna Bogucka
摘要：
摘要：
【2】Knowledge-Guided Retrieval-Augmented Generation for Zero-Shot Psychiatric Data: Privacy Preserving Synthetic Data Generation
标题：Zero-Shot精神病学数据的知识引导检索增强生成：隐私保护合成数据生成
链接：https://arxiv.org/abs/2603.25186
作者：Adam Jakobsen, Sushant Gautam, Hugo Lewi Hammer, Susanne Olofsdotter, Miriam S Johanson, Pål Halvorsen, Vajira Thambawita
备注：Submitted to CBMS 2026
摘要：
摘要：
【3】Synthetic Cardiac MRI Image Generation using Deep Generative Models
标题：使用深度生成模型生成合成心脏MRI图像
链接：https://arxiv.org/abs/2603.24764
作者：Ishan Kumarasinghe, Dasuni Kawya, Madhura Edirisooriya, Isuri Devindi, Isuru Nawinne, Vajira Thambawita
备注：12 pages, 2 figures, Preprint
摘要：
摘要：
【4】AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation
标题：AutoSam：一个用于通过多模式检索增强生成自动生成Sam代码的输入文件的抽象框架
链接：https://arxiv.org/abs/2603.24736
作者：Zaid Abulawi (1 and 2), Zavier Ndum Ndum (1 and 2), Eric Cervi (2), Rui Hu (2), Yang Liu (1) ((1) Department of Nuclear Engineering, Texas A&M University, (2) Nuclear Science and Engineering Division, Argonne National Laboratory)
备注：34 Pages, 14 Figures
摘要：
摘要：
半/弱/无/有监督|不确定性|主动学习(3篇)
【1】Uncertainty-Guided Label Rebalancing for CPS Safety Monitoring
标题：CPS安全监控的不确定性引导标签重新平衡
链接：https://arxiv.org/abs/2603.25670
作者：John Ayotunde, Qinghua Xu, Guancheng Wang, Lionel C. Briand
备注：10 pages (main content), 3 pages references, 5 figures, 5 tables. Under review
摘要：
摘要：
【2】SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment
标题：SAVe：利用视觉伪影和视听错位的自我监督视听Deepfake检测
链接：https://arxiv.org/abs/2603.25140
作者：Sahibzada Adil Shahzad, Ammarah Hashmi, Junichi Yamagishi, Yusuke Yasuda, Yu Tsao, Chia-Wen Lin, Yan-Tsung Peng, Hsin-Min Wang
摘要：
摘要：
【3】GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining
标题：GoldiCLIP：平衡图像预训练显式监督的Goldilocks方法
链接：https://arxiv.org/abs/2603.24804
作者：Deen Dayal Mohan, Hossein Souri, Vitali Petsiuk, Juhong Min, Gopal Sharma, Luowei Zhou, Suren Kumar
摘要：
摘要：
迁移|Zero/Few/One-Shot|自适应(5篇)
【1】No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models
标题：不需要硬性否定：以概念为中心的学习可以在不降低对比模型的Zero-Shot能力的情况下实现组合性
链接：https://arxiv.org/abs/2603.25722
作者：Hai X. Pham, David T. Hoffmann, Ricardo Guerrero, Brais Martinez
备注：Accepted at CVPR 2026
摘要：
摘要：
【2】How Class Ontology and Data Scale Affect Audio Transfer Learning
标题：类本体和数据规模如何影响音频迁移学习
链接：https://arxiv.org/abs/2603.25476
作者：Manuel Milling, Andreas Triantafyllopoulos, Alexander Gebhard, Simon Rampp, Björn W. Schuller
摘要：
摘要：
【3】Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning
标题：Sim 2RealZero-Shot强化学习的最大熵行为探索
链接：https://arxiv.org/abs/2603.25464
作者：Jiajun Hu, Nuria Armengol Urpi, Jin Cheng, Stelian Coros
摘要：
摘要：
【4】Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous Decision Making in Sustainable and Resilient Industrial Networks
标题：通过可持续和有弹性的工业网络中的自适应资源持有和自主决策实现联邦学习的静态信任协调
链接：https://arxiv.org/abs/2603.25334
作者：Paul Shepherd, Tasos Dagiuklas, Bugra Alkan, Jonathan Rodriguez
摘要：
摘要：
【5】Autotuning T-PaiNN: Enabling Data-Efficient GNN Interatomic Potential Development via Classical-to-Quantum Transfer Learning
标题：自动调整T-PaiNN：通过经典到量子转移学习实现数据高效的GNN原子间潜力开发
链接：https://arxiv.org/abs/2603.24752
作者：Vivienne Pelletier, Vedant Bhat, Daniel J. Rivera, Steven A. Wilson, Christopher L. Muhich
备注：19 pages, 7 figures
摘要：
摘要：
强化学习(3篇)
【1】Cooperative Deep Reinforcement Learning for Fair RIS Allocation
标题：用于RIS公平分配的协同深度强化学习
链接：https://arxiv.org/abs/2603.25572
作者：Martin Mark Zan, Stefan Schwarz
摘要：
摘要：
【2】Decentralized Task Scheduling in Distributed Systems: A Deep Reinforcement Learning Approach
标题：分布式系统中的分散任务调度：深度强化学习方法
链接：https://arxiv.org/abs/2603.24738
作者：Daniel Benniah John
备注：12 pages, 8 figures. Under review. Code available at GitHub
摘要：
摘要：
【3】Reinforcement learning for quantum processes with memory
标题：具有记忆的量子过程的强化学习
链接：https://arxiv.org/abs/2603.25138
作者：Josep Lumbreras, Ruo Cheng Huang, Yanglin Hu, Marco Fanizza, Mile Gu
备注：85 pages, 5 figures
摘要：
摘要：
医学相关(1篇)
【1】A Practical Guide Towards Interpreting Time-Series Deep Clinical Predictive Models: A Reproducibility Study
标题：解读时间序列深度临床预测模型的实用指南：再现性研究
链接：https://arxiv.org/abs/2603.24828
作者：Yongda Fan, John Wu, Andrea Fitzpatrick, Naveen Baskaran, Jimeng Sun, Adam Cross
备注：Under Review
摘要：
摘要：
蒸馏|知识提取(3篇)
【1】Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
标题：重新审视政策蒸馏：经验失败模式和简单修复
链接：https://arxiv.org/abs/2603.25562
作者：Yuqian Fu, Haohuan Huang, Kaiwen Jiang, Yuanheng Zhu, Dongbin Zhao
摘要：
摘要：
【2】A Public Theory of Distillation Resistance via Constraint-Coupled Reasoning Architectures
标题：通过约束耦合推理体系结构的蒸馏阻力公开理论
链接：https://arxiv.org/abs/2603.25022
作者：Peng Wei, Wesley Shu
摘要：
摘要：
【3】Physics-Informed Neural Network Digital Twin for Dynamic Tray-Wise Modeling of Distillation Columns under Transient Operating Conditions
标题：物理信息神经网络数字双胞胎，用于在瞬时操作条件下对蒸馏塔进行动态托盘建模
链接：https://arxiv.org/abs/2603.24644
作者：Debadutta Patra, Ayush Bardhan Tripathy, Soumya Ranjan Sahu, Sucheta Panda
备注：17 pages, 10 figures
摘要：
摘要：
推荐(1篇)
【1】Pseudo Label NCF for Sparse OHC Recommendation: Dual Representation Learning and the Separability Accuracy Trade off
标题：Sparse OHC的伪标签NCF建议：双重表示学习和可分离性准确性权衡
链接：https://arxiv.org/abs/2603.24750
作者：Pronob Kumar Barman, Tera L. Reynolds. James Foulds
摘要：
摘要：
自动驾驶|车辆|车道检测等(3篇)
【1】Challenges in Hyperspectral Imaging for Autonomous Driving: The HSI-Drive Case
标题：用于自动驾驶的高光谱成像挑战：HSI-Drive案例
链接：https://arxiv.org/abs/2603.25510
作者：Koldo Basterretxea, Jon Gutiérrez-Zaballa, Javier Echanobe
摘要：
摘要：
【2】Lightweight GenAI for Network Traffic Synthesis: Fidelity, Augmentation, and Classification
标题：用于网络流量合成的轻量级GenAI：保真度、增强和分类
链接：https://arxiv.org/abs/2603.25507
作者：Giampaolo Bovenzi, Domenico Ciuonzo, Jonatan Krolikowski, Antonio Montieri, Alfredo Nascita, Antonio Pescapè, Dario Rossi
备注：7 pages, 3 figures, 3 tables, 4 research questions, preprint submitted to IEEE Communications Magazine
摘要：
摘要：
【3】Ultra-fast Traffic Nowcasting and Control via Differentiable Agent-based Simulation
标题：通过基于差异代理的模拟实现超快交通预播和控制
链接：https://arxiv.org/abs/2603.25068
作者：Fumiyasu Makinoshima, Yuya Yamaguchi, Eigo Segawa, Koichiro Niinuma, Sean Qian
摘要：
摘要：
点云|SLAM|雷达|激光|深度RGBD相关(1篇)
【1】A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization
标题：Grokking的系统性实证研究：深度、架构、激活和规则化
链接：https://arxiv.org/abs/2603.25009
作者：Shalima Binta Manir, Anamika Paul Rupa
摘要：
摘要：
推理|分析|理解|解释(10篇)
【1】LanteRn: Latent Visual Structured Reasoning
标题：LanteRN：潜在的视觉结构推理
链接：https://arxiv.org/abs/2603.25629
作者：André G. Viveiros, Nuno Gonçalves, Matthias Lindemann, André Martins
摘要：
摘要：
【2】Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference
标题：用于分类推理的层次引导多模式表示学习
链接：https://arxiv.org/abs/2603.25573
作者：Sk Miraj Ahmed, Xi Yu, Yunqi Li, Yuewei Lin, Wei Xu
备注：Accepted at the ICLR 2026 Workshop on Foundation Models for Science (FM4Science)
摘要：
摘要：
【3】Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding
标题：解释的正确性重要吗？将计算XAI评估与人类理解联系起来
链接：https://arxiv.org/abs/2603.25251
作者：Gregor Baer, Chao Zhang, Isel Grau, Pieter Van Gorp
备注：24 pages, 9 figures, 2 tables
摘要：
摘要：
【4】Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
标题：移动边缘训练：在线验证的即时选择，以实现大型推理模型的高效RL训练
链接：https://arxiv.org/abs/2603.25184
作者：Jiahao Wu, Ning Lu, Shengcai Liu, Kun Wang, Yanting Yang, Li Qing, Ke Tang
摘要：
摘要：
【5】An Explainable Ensemble Learning Framework for Crop Classification with Optimized Feature Pyramids and Deep Networks
标题：具有优化特征金字塔和深度网络的作物分类可解释的集成学习框架
链接：https://arxiv.org/abs/2603.25070
作者：Syed Rayhan Masud, SK Muktadir Hossain, Md. Ridoy Sarkar, Mohammad Sakib Mahmood, Md. Kishor Morol, Rakib Hossain Sajib
摘要：
摘要：
【6】TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization
标题：TopoPilot：可靠的对话式工作流程自动化，用于布局数据分析和可视化
链接：https://arxiv.org/abs/2603.25063
作者：Nathaniel Gorski, Shusen Liu, Bei Wang
摘要：
摘要：
【7】Dissecting Model Failures in Abdominal Aortic Aneurysm Segmentation through Explainability-Driven Analysis
标题：基于可解释性驱动的腹主动脉瘤分割中的解剖模型失效
链接：https://arxiv.org/abs/2603.24801
作者：Abu Noman Md Sakib, Merjulah Roby, Zijie Zhang, Satish Muluk, Mark K. Eskandari, Ender A. Finol
摘要：
摘要：
【8】Causal AI For AMS Circuit Design: Interpretable Parameter Effects Analysis
标题：AMS电路设计的因果人工智能：可解释参数效应分析
链接：https://arxiv.org/abs/2603.24618
作者：Mohyeu Hussain, David Koblah, Reiner Dizon-Paradis, Domenic Forte
摘要：
摘要：
【9】Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks
标题：通过等变神经网络进行相关离散选择模型的摊销推理
链接：https://arxiv.org/abs/2603.24705
作者：Easton Huch, Michael Keane
摘要：
摘要：
【10】A Large-Scale Comparative Analysis of Imputation Methods for Single-Cell RNA Sequencing Data
标题：单细胞RNA测序数据插补方法的大规模比较分析
链接：https://arxiv.org/abs/2603.24626
作者：Yuichiro Iwashita, Ahtisham Fazeel Abbasi, Muhammad Nabeel Asim, Andreas Dengel
摘要：
摘要：
检测相关(4篇)
【1】Knowledge-Guided Failure Prediction: Detecting When Object Detectors Miss Safety-Critical Objects
标题：知识引导的故障预测：检测对象检测器何时错过安全关键对象
链接：https://arxiv.org/abs/2603.25499
作者：Jakob Paul Zimmermann, Gerrit Holzbach, David Lerch
摘要：
摘要：
【2】Hyperspectral Trajectory Image for Multi-Month Trajectory Anomaly Detection
标题：用于多个月轨迹异常检测的高光谱轨迹图像
链接：https://arxiv.org/abs/2603.25255
作者：Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati, B. S. Manjunath
摘要：
摘要：
【3】Towards automatic smoke detector inspection: Recognition of the smoke detectors in industrial facilities and preparation for future drone integration
标题：自动烟雾探测器检测：识别工业设施中的烟雾探测器，为未来的无人机集成做准备
链接：https://arxiv.org/abs/2603.24850
作者：Lukas Kratochvila, Jakub Stefansky, Simon Bilik, Robert Rous, Tomas Zemcik, Michal Wolny, Frantisek Rusnak, Ondrej Cech, Karel Horak
摘要：
摘要：
【4】Energy-Efficient Hierarchical Federated Anomaly Detection for the Internet of Underwater Things via Selective Cooperative Aggregation
标题：通过选择性合作聚合实现水下物联网的节能分层联邦异常检测
链接：https://arxiv.org/abs/2603.24648
作者：Kenechi Omeke, Michael Mollel, Lei Zhang, Qammer H. Abbasi, Muhammad Ali Imran
摘要：
摘要：
分类|识别(1篇)
【1】Insights on back marking for the automated identification of animals
标题：对动物自动识别背面标记的见解
链接：https://arxiv.org/abs/2603.25535
作者：David Brunner, Marie Bordes, Elisabeth Mayrhuber, Stephan M. Winkler, Viktoria Dorfer, Maciej Oczak
摘要：
摘要：
表征(2篇)
【1】Layer-Specific Lipschitz Modulation for Fault-Tolerant Multimodal Representation Learning
标题：用于故障容忍多模式表示学习的特定层Lipschitz调制
链接：https://arxiv.org/abs/2603.25103
作者：Diyar Altinses, Andreas Schwung
摘要：
摘要：
【2】Demystifying When Pruning Works via Representation Hierarchies
标题：通过表示层次结构揭开修剪何时有效的神秘面纱
链接：https://arxiv.org/abs/2603.24652
作者：Shwai He, Guoheng Sun, Haichao Zhang, Yun Fu, Ang Li
备注：26 pages, 21 figures, Table 3
摘要：
摘要：
3D|3D重建等相关(1篇)
【1】CSI-tuples-based 3D Channel Fingerprints Construction Assisted by MultiModal Learning
标题：多模式学习辅助的基于CSC二元组的3D通道指纹构建
链接：https://arxiv.org/abs/2603.25288
作者：Chenjie Xie, Li You, Ruirong Chen, Gaoning He, Xiqi Gao
备注：14 pages, 9 figures
摘要：
摘要：
编码器(1篇)
【1】Spatiotemporal System Forecasting with Irregular Time Steps via Masked Autoencoder
标题：通过掩蔽自动编码器进行不规则时间步的时空系统预测
链接：https://arxiv.org/abs/2603.25597
作者：Kewei Zhu, Yanze Xin, Jinwei Hu, Xiaoyuan Cheng, Yiming Yang, Sibo Cheng
摘要：
摘要：
优化|敛散性(5篇)
【1】Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?
标题：用于高级合成的代理工厂：通用编码代理在硬件优化中能走多远？
链接：https://arxiv.org/abs/2603.25719
作者：Abhishek Bhandwaldar, Mihir Choudhury, Ruchir Puri, Akash Srivastava
摘要：
摘要：
【2】Optimal High-Probability Regret for Online Convex Optimization with Two-Point Bandit Feedback
标题：具有两点Bandit反馈的在线凸优化的最优高概率后悔
链接：https://arxiv.org/abs/2603.25029
【3】Can an Actor-Critic Optimization Framework Improve Analog Design Optimization?
标题：演员评论家优化框架能否改善模拟设计优化？
链接：https://arxiv.org/abs/2603.24714
作者：Sounak Dutta, Fin Amin, Sushil Panda, Jonathan Rabe, Yuejiang Wen, Paul Franzon
备注：7 pages, 5 figures
摘要：
摘要：
【4】Enabling ab initio geometry optimization of strongly correlated systems with transferable deep quantum Monte Carlo
标题：利用可转移深度量子蒙特卡罗实现强相关系统的从头算几何优化
链接：https://arxiv.org/abs/2603.25381
作者：P. Bernát Szabó, Zeno Schätzle, Frank Noé
备注：20 pages, 8 figures
摘要：
摘要：
【5】Practical Efficient Global Optimization is No-regret
标题：实用高效的全局优化无悔
链接：https://arxiv.org/abs/2603.25311
作者：Jingyi Wang, Haowei Wang, Nai-Yuan Chiang, Juliane Mueller, Tucker Hartland, Cosmin G. Petra
摘要：
摘要：
预测|估计(8篇)
【1】An Integrative Genome-Scale Metabolic Modeling and Machine Learning Framework for Predicting and Optimizing Biofuel-Relevant Biomass Production in Saccharomyces cerevisiae
标题：用于预测和优化酿酒酵母生物燃料相关生物量生产的集成基因组规模代谢建模和机器学习框架
链接：https://arxiv.org/abs/2603.25561
作者：Neha K. Nair, Aaron D'Souza
备注：8 pages, 12 figures, and 2 tables
摘要：
摘要：
【2】Interpretable PM2.5 Forecasting for Urban Air Quality: A Comparative Study of Operational Time-Series Models
标题：城市空气质量可解释PM2.5预报：业务时间序列模型的比较研究
链接：https://arxiv.org/abs/2603.25495
作者：Moazzam Umer Gondal, Hamad ul Qudous, Asma Ahmad Farhan, Sultan Alamri
备注：Submitted to PLOS ONE
摘要：
摘要：
【3】A CDF-First Framework for Free-Form Density Estimation
标题：DF优先的自由形式密度估计框架
链接：https://arxiv.org/abs/2603.25204
作者：Chenglong Song, Mazharul Islam, Lin Wang, Bing Chen, Bo Yang
摘要：
摘要：
【4】MP-MoE: Matrix Profile-Guided Mixture of Experts for Precipitation Forecasting
标题：MP-MoE：矩阵配置文件引导的降水预测专家混合
链接：https://arxiv.org/abs/2603.25046
作者：Huyen Ngoc Tran, Dung Trung Tran, Hong Nguyen, Xuan Vu Phan, Nam-Phong Nguyen
摘要：
摘要：
【5】Conformal Prediction for Nonparametric Instrumental Regression
标题：非参数工具回归的保形预测
链接：https://arxiv.org/abs/2603.25509
【6】Residual-as-Teacher: Mitigating Bias Propagation in Student--Teacher Estimation
标题：留守教师：减轻学生中的偏见传播--教师估计
链接：https://arxiv.org/abs/2603.25466
作者：Kakei Yamamoto, Martin J. Wainwright
摘要：
摘要：
【7】A Distribution-to-Distribution Neural Probabilistic Forecasting Framework for Dynamical Systems
标题：动态系统的分布到分布神经概率预测框架
链接：https://arxiv.org/abs/2603.25370
作者：Tianlin Yang, Hailiang Du, Louis Aslett
备注：11 pages,5 figures
摘要：
摘要：
【8】Conformal Selective Prediction with General Risk Control
标题：具有一般风险控制的保形选择性预测
链接：https://arxiv.org/abs/2603.24704
作者：Tian Bai, Ying Jin
摘要：
摘要：
其他神经网络|深度学习|模型|建模(19篇)
【1】Neural Network Conversion of Machine Learning Pipelines
标题：机器学习管道的神经网络转换
链接：https://arxiv.org/abs/2603.25699
作者：Man-Ling Sung, Jan Silovsky, Man-Hung Siu, Herbert Gish, Chinnu Pittapally
备注：Submitted and accepted to AutoML 2018 @ ICML/IJCAI-ECAI
摘要：
摘要：
【2】Social Hippocampus Memory Learning
标题：社交海马记忆学习
链接：https://arxiv.org/abs/2603.25614
作者：Liping Yi, Zhiming Zhao, Qinghua Hu
摘要：
摘要：
【3】Causal-INSIGHT: Probing Temporal Models to Extract Causal Structure
标题：Cause-INSIGHT：探测时间模型以提取因果结构
链接：https://arxiv.org/abs/2603.25473
作者：Benjamin Redden, Hui Wang, Shuyan Li
备注：Accepted at IJCNN, 2026
摘要：
摘要：
【4】Not a fragment, but the whole: Map-based evaluation of data-driven Fire Danger Index models
标题：不是片段，而是整体：基于地图的数据驱动火灾危险指数模型评估
链接：https://arxiv.org/abs/2603.25469
作者：Shahbaz Alvi, Italo Epicoco, Jose Maria Costa Saura
备注：20 pages, 8 figures, 3 tables
摘要：
摘要：
【5】Hessian-informed machine learning interatomic potential towards bridging theory and experiments
标题：黑森式机器学习原子间潜力连接理论和实验
链接：https://arxiv.org/abs/2603.25373
作者：Bangchen Yin, Jian Ouyang, Zhen Fan, Kailai Lin, Hanshi Hu, Dingshun Lv, Weiluo Ren, Hai Xiao, Ji Chen, Changsu Cao
备注：13 pages, 4 figures
摘要：
摘要：
【6】An Image Dataset of Common Skin Diseases of Bangladesh and Benchmarking Performance with Machine Learning Models
标题
：孟加拉国常见皮肤病的图像数据集以及使用机器学习模型进行性能基准测试
链接：https://arxiv.org/abs/2603.25229
作者：Sazzad Hossain, Saiful Islam, Muhammad Ibrahim, Md. Rasel Ahmed, Md Shuayb, Ahmedul Kabir
备注：14 pages
摘要：
摘要：
【7】Vision Hopfield Memory Networks
标题：愿景霍普菲尔德记忆网络
链接：https://arxiv.org/abs/2603.25157
作者：Jianfeng Wang, Amine M'Charrak, Luk Koska, Xiangtao Wang, Daniel Petriceanu, Mykyta Smyrnov, Ruizhi Wang, Michael Bumbar, Luca Pinchetti, Thomas Lukasiewicz
摘要：
摘要：
【8】Learning to Rank Caption Chains for Video-Text Alignment
标题：学习对字幕链进行排名以实现视频文本对齐
链接：https://arxiv.org/abs/2603.25145
作者：Ansel Blume, Burak Uzkent, Shalini Chaudhuri, Garin Kessler
摘要：
摘要：
【9】Process-Aware AI for Rainfall-Runoff Modeling: A Mass-Conserving Neural Framework with Hydrological Process Constraints
标题：用于降雨径流建模的过程感知人工智能：具有水文过程约束的质量保护神经框架
链接：https://arxiv.org/abs/2603.25093
作者：Mohammad A. Farmani, Hoshin V. Gupta, Ali Behrangi, Muhammad Jawad, Sadaf Moghisi, Guo-Yue Niu
摘要：
摘要：
【10】Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
标题：Intern-S1-Pro：万亿级的科学多峰基础模型
链接：https://arxiv.org/abs/2603.25040
作者：Yicheng Zou, Dongsheng Zhu, Lin Zhu, Tong Zhu, Yunhua Zhou, Peiheng Zhou, Xinyu Zhou, Dongzhan Zhou, Zhiwang Zhou, Yuhao Zhou, Bowen Zhou, Zhanping Zhong, Zhijie Zhong, Haiteng Zhao, Penghao Zhao, Xiaomeng Zhao, Zhiyuan Zhao, Yechen Zhang, Jin Zhang, Wenwei Zhang, Hongjie Zhang, Zhuo Zhang, Wenlong Zhang, Bo Zhang, Chao Zhang, Chen Zhang, Yuhang Zang, Fei Yuan, Jiakang Yuan, Jiashuo Yu, Jinhui Yin, Haochen Ye, Qian Yao, Bowen Yang, Danni Yang, Kaichen Yang, Ziang Yan, Jun Xu, Yicheng Xu, Wanghan Xu, Xuenan Xu, Chao Xu, Ruiliang Xu, Shuhao Xing, Long Xing, Xinchen Xie, Ling-I Wu, Zijian Wu, Zhenyu Wu, Lijun Wu, Yue Wu, Jianyu Wu, Wen Wu, Fan Wu, Xilin Wei, Qi Wei, Bingli Wang, Rui Wang, Ziyi Wang, Zun Wang, Yi Wang, Haomin Wang, Yizhou Wang, Lintao Wang, Yiheng Wang, Longjiang Wang, Bin Wang, Jian Tong, Zhongbo Tian, Huanze Tang, Chen Tang, Shixiang Tang, Yu Sun, Qiushi Sun, Xuerui Su, Qisheng Su, Chenlin Su, Demin Song, Jin Shi, Fukai Shang, Yuchen Ren, Pengli Ren, Xiaoye Qu, Yuan Qu, Jiantao Qiu, Yu Qiao, Runyu Peng, Tianshuo Peng, Jiahui Peng, Qizhi Pei, Zhuoshi Pan, Linke Ouyang, Wenchang Ning, Yichuan Ma, Zerun Ma, Ningsheng Ma, Runyuan Ma, Chengqi Lyu, Haijun Lv, Han Lv
摘要：
摘要：
【11】Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems
标题：一次设计，大规模部署：大型模型生态系统的模板驱动ML开发
链接：https://arxiv.org/abs/2603.24963
作者：Jiang Liu, John Martabano Landy, Yao Xuan, Swamy Muddu, Nhat Le, Munaf Sahaf, Luc Kien Hang, Rupinder Khandpour, Kevin De Angeli, Chang Yang, Shouyuan Chen, Shiblee Sadik, Ani Agrawal, Djordje Gligorijevic, Jingzheng Qin, Peggy Yao, Alireza Vahdatpour
摘要：
摘要：
【12】AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
标题：基础模型时代的人工智能安全：统一视角的全面调查
链接：https://arxiv.org/abs/2603.24857
作者：Zhenyi Wang, Siyu Luan
备注：Published at Transactions on Machine Learning Research (TMLR)
摘要：
摘要：
【13】Local learning for stable backpropagation-free neural network training towards physical learning
标题：本地学习，实现稳定的无反向传播神经网络训练，以实现物理学习
链接：https://arxiv.org/abs/2603.24790
作者：Yaqi Guo, Fabian Braun, Bastiaan Ketelaar, Stephanie Tan, Richard Norte, Siddhant Kumar
摘要：
摘要：
【14】Contrastive Learning Boosts Deterministic and Generative Models for Weather Data
标题：对比学习增强天气数据的确定性和生成性模型
链接：https://arxiv.org/abs/2603.24744
【15】How unconstrained machine-learning models learn physical symmetries
标题：无约束机器学习模型如何学习物理对称性
链接：https://arxiv.org/abs/2603.24638
作者：Michelangelo Domina, Joseph William Abbott, Paolo Pegolo, Filippo Bigi, Michele Ceriotti
备注：15 pages, 9 figures
摘要：
摘要：
【16】The Rules-and-Facts Model for Simultaneous Generalization and Memorization in Neural Networks
标题：神经网络中同时概括和精简的规则与事实模型
链接：https://arxiv.org/abs/2603.25579
作者：Gabriele Farné, Fabrizio Boncoraglio, Lenka Zdeborová
摘要：
摘要：
【17】Improving Infinitely Deep Bayesian Neural Networks with Nesterov's Accelerated Gradient Method
标题：用Nesterov的加速梯度方法改进无限深度Bayesian神经网络
链接：https://arxiv.org/abs/2603.25024
作者：Chenxu Yu, Wenqi Fang
摘要：
摘要：
【18】Binary Expansion Group Intersection Network
标题：二元扩展群交叉网络
链接：https://arxiv.org/abs/2603.24763
作者：Sicheng Zhou, Kai Zhang
摘要：
摘要：
【19】Spectral methods: crucial for machine learning, natural for quantum computers?
标题：光谱方法：对机器学习至关重要，对量子计算机来说自然？
链接：https://arxiv.org/abs/2603.24654
作者：Vasilis Belis, Joseph Bowles, Rishabh Gupta, Evan Peters, Maria Schuld
备注：25 pages, 8 figures
摘要：
摘要：
其他(28篇)
【1】A Unified Memory Perspective for Probabilistic Trustworthy AI
标题：概率可信人工智能的统一记忆视角
链接：https://arxiv.org/abs/2603.25692
作者：Xueji Zhao, Likai Pei, Jianbo Liu, Kai Ni, Ningyuan Cao
摘要：
摘要：
【2】On Neural Scaling Laws for Weather Emulation through Continual Training
标题：基于连续训练的天气模拟神经标度律研究
链接：https://arxiv.org/abs/2603.25687
作者：Shashank Subramanian, Alexander Kiefer, Arnur Nigmetov, Amir Gholami, Dmitriy Morozov, Michael W. Mahoney
备注：ICLR Foundation Models for Science Workshop 2026, 19 pages, 13 figures
摘要：
摘要：
【3】Longitudinal Digital Phenotyping for Early Cognitive-Motor Screening
标题：纵向数字表型分析用于早期认知运动筛查
链接：https://arxiv.org/abs/2603.25673
作者：Diego Jimenez-Oviedo, Ruben Vera-Rodriguez, Ruben Tolosana, Juan Carlos Ruiz-Garcia, Jaime Herreros-Rodriguez
备注：IEEE CAI 2026 6 Pages 2 Figures
摘要：
摘要：
【4】The Geometry of Efficient Nonconvex Sampling
标题：有效非凸采样的几何
链接：https://arxiv.org/abs/2603.25622
作者：Santosh S. Vempala, Andre Wibisono
摘要：
摘要：
【5】Missing-Aware Multimodal Fusion for Unified Microservice Incident Management
标题：用于统一微服务事件管理的缺失感知多模式融合
链接：https://arxiv.org/abs/2603.25538
作者：Wenzhuo Qian, Hailiang Zhao, Ziqi Wang, Zhipeng Gao, Jiayi Chen, Zhiwei Ling, Shuiguang Deng
摘要：
摘要：
【6】NERO-Net: A Neuroevolutionary Approach for the Design of Adversarially Robust CNNs
标题：NERO-Net：一种用于设计对抗鲁棒CNN的神经进化方法
链接：https://arxiv.org/abs/2603.25517
作者：Inês Valentim, Nuno Antunes, Nuno Lourenço
摘要：
摘要：
【7】Decidable By Construction: Design-Time Verification for Trustworthy AI
标题：可由结构决定：值得信赖的人工智能的设计时验证
链接：https://arxiv.org/abs/2603.25414
作者：Houston Haynes
备注：18 pages, 1 figure
摘要：
摘要：
【8】Supercharging Federated Intelligence Retrieval
标题：增强联邦情报检索
链接：https://arxiv.org/abs/2603.25374
作者：Dimitris Stripelis, Patrick Foley, Mohammad Naseri, William Lindskog-Münzing, Chong Shen Ng, Daniel Janes Beutel, Nicholas D. Lane
备注：6 pages, 1 figure, 2 tables
摘要：
摘要：
【9】From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents
标题：从意图到证据：深度研究代理结构评估的分类方法
链接：https://arxiv.org/abs/2603.25342
作者：Shuoling Liu, Zhiquan Tan, Kun Yi, Hui Wu, Yihan Li, Jiangpeng Yan, Liyuan Chen, Kai Chen, Qiang Yang
摘要：
摘要：
【10】Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages
标题：翻译还是背诵？校准极低资源语言的机器翻译的评估分数
链接：https://arxiv.org/abs/2603.25222
作者：Danlu Chen, Ka Sing He, Jiahe Tian, Chenghao Xiao, Zhaofeng Wu, Taylor Berg-Kirkpatrick, Freda Shi
摘要：
摘要：
【11】Gap Safe Screening Rules for Fast Training of Robust Support Vector Machines under Feature Noise
标题：特征噪音下鲁棒支持向量机快速训练的间隙安全筛选规则
链接：https://arxiv.org/abs/2603.25221
作者：Tan-Hau Nguyen, Thu-Le Tran, Kien Trung Nguyen
备注：19 pages
摘要：
摘要：
【12】Goodness-of-pronunciation without phoneme time alignment
标题：没有音素时间对齐的发音良好度
链接：https://arxiv.org/abs/2603.25150
作者：Jeremy H. M. Wong, Nancy F. Chen
摘要：
摘要：
【13】Robust Principal Component Completion
标题：稳健的主成分完成
链接：https://arxiv.org/abs/2603.25132
作者：Yinjian Wang, Wei Li, Yuanyuan Gui, James E. Fowler, Gemine Vivone
摘要：
摘要：
【14】SEVerA: Verified Synthesis of Self-Evolving Agents
标题：SEVerA：自我进化试剂的验证合成
链接：https://arxiv.org/abs/2603.25111
作者：Debangshu Banerjee, Changming Xu, Gagandeep Singh
备注：Formally Verified Self-Evolving LLM Agents
摘要：
摘要：
【15】The Order Is The Message
标题：命令就是信息
链接：https://arxiv.org/abs/2603.25047
作者：Jordan LeDoux
备注：51 pages, 12 figures
摘要：
摘要：
【16】Epistemic Compression: The Case for Deliberate Ignorance in High-Stakes AI
标题：认识压缩：高风险人工智能中故意无知的案例
链接：https://arxiv.org/abs/2603.25033
作者：Steffen Lukas
备注：28 pages, 6 figures
摘要：
摘要：
【17】CVA: Context-aware Video-text Alignment for Video Temporal Grounding
标题：CVA：上下文感知的视频-文本对齐，以实现视频时间基础
链接：https://arxiv.org/abs/2603.24934
作者：Sungho Moon, Seunghun Lee, Jiwan Seo, Sunghoon Im
备注：Accepted to CVPR 2026
摘要：
摘要：
【18】Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML
标题：一次性通道混音器（HyperPERTINYPW）：TinyML的生成压缩
链接：https://arxiv.org/abs/2603.24916
作者：Yassien Shaalan
备注：12 pages, 5 figures. Accepted at MLSys 2026. TinyML / on-device learning paper on hypernetwork-based compression for ECG and other 1D biosignals, with integer-only inference on commodity MCUs. Evaluated on Apnea-ECG, PTB-XL, and MIT-BIH. Camera-ready version with additional datasets, experiments, and insights will appear after May 2026
摘要：
摘要：
【19】Flow matching on homogeneous spaces
标题：齐次空间上的流匹配
链接：https://arxiv.org/abs/2603.24829
作者：Francesco Ruscelli
备注：10 pages
摘要：
摘要：
【20】Light Cones For Vision: Simple Causal Priors For Visual Hierarchy
标题：视觉光锥：视觉层次的简单因果先验
链接：https://arxiv.org/abs/2603.24753
作者：Manglam Kartik, Neel Tushar Shah
备注：ICLR GRaM Workshop 2026
摘要：
摘要：
【21】Grokking as a Falsifiable Finite-Size Transition
标题：Grokking是一种不可证伪的伪君子规模转变
链接：https://arxiv.org/abs/2603.24746
作者：Yuda Bi, Chenyu Zhang, Qiheng Wang, Vince D Calhoun
摘要：
摘要：
【22】Trust as Monitoring: Evolutionary Dynamics of User Trust and AI Developer Behaviour
标题：信任即监控：用户信任和人工智能开发人员行为的进化动力学
链接：https://arxiv.org/abs/2603.24742
作者：Adeela Bashir, Zhao Song, Ndidi Bianca Ogbo, Nataliya Balabanova, Martin Smit, Chin-wing Leung, Paolo Bova, Manuel Chica Serrano, Dhanushka Dissanayake, Manh Hong Duong, Elias Fernandez Domingos, Nikita Huber-Kralj, Marcus Krellner, Andrew Powell, Stefan Sarkadi, Fernando P. Santos, Zia Ush Shamszaman, Chaimaa Tarzi, Paolo Turrini, Grace Ibukunoluwa Ufeoshi, Victor A. Vargas-Perez, Alessandro Di Stefano, Simon T. Powers, The Anh Han
摘要：
摘要：
【23】Amplified Patch-Level Differential Privacy for Free via Random Cropping
标题：通过随机裁剪免费增强补丁级差异隐私
链接：https://arxiv.org/abs/2603.24695
作者：Kaan Durmaz, Jan Schuchardt, Sebastian Schmidt, Stephan Günnemann
备注：Published at TMLR
摘要：
摘要：
【24】The Symmetric Perceptron: a Teacher-Student Scenario
标题：对称感知器：师生场景
链接：https://arxiv.org/abs/2603.25440
作者：Giovanni Catania, Aurélien Decelle, Suhanee Korpe
备注：19 pages, 6 figures
摘要：
摘要：
【25】A Causal Framework for Evaluating ICU Discharge Strategies
标题：评价ICU出院策略的因果框架
链接：https://arxiv.org/abs/2603.25397
作者：Sagar Nagaraj Simha, Juliette Ortholand, Dave Dongelmans, Jessica D. Workum, Olivier W.M. Thijssens, Ameen Abu-Hanna, Giovanni Cinà
备注：8 pages, 2 figures, 2 tables
摘要：
摘要：
【26】Fair regression under localized demographic parity constraints
标题：局部人口平价约束下的公平回归
链接：https://arxiv.org/abs/2603.25224
作者：Arthur Charpentier (UQAM), Christophe Denis (SAMM), Romuald Elie (LAMA), Mohamed Hebiri (LAMA), François HU (UdeM)
摘要：
摘要：
【27】The Value of Information in Resource-Constrained Pricing
标题：资源约束定价中的信息价值
链接：https://arxiv.org/abs/2603.24974
作者：Ruicheng Ao, Jiashuo Jiang, David Simchi-Levi
备注：Extended version of the NeurIPS 2025 paper (arXiv:2501.14155). This version adds phase transition, surrogate-assisted variance reduction under model misspecification, and numerical experiments
摘要：
摘要：
【28】Response-Aware Risk-Constrained Control Barrier Function With Application to Vehicles
标题：响应感知风险约束控制屏障功能及其应用于车辆
链接：https://arxiv.org/abs/2603.24598
作者：Qijun Liao, Jue Yang
备注：22 pages, 20 figures
摘要：
摘要：
机器翻译由腾讯交互翻译提供，仅供参考
点击“阅读原文”获取带摘要的学术速递
