机器学习学术速递[8.5]

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312篇

大模型相关(43篇)

【1】LOST: Low-rank and Sparse Pre-training for Large Language Models
标题：LOST：大型语言模型的低等级和稀疏预训练
链接：https://arxiv.org/abs/2508.02668

作者： Lu Yin, Li Shen, Jinjin Xu, Liwu Xu, Tianjin Huang, Wenwu Wang, Shiwei Liu, Xilu Wang

【2】StructSynth: Leveraging LLMs for Structure-Aware Tabular Data Synthesis in Low-Data Regimes
标题：StructSynth：利用LLM进行低数据机制中的结构感知表格数据合成
链接：https://arxiv.org/abs/2508.02601

作者： Yujia Zheng, Yongqi Zhang

【3】CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge
标题：CAMA：利用因果知识增强大型语言模型中的数学推理
链接：https://arxiv.org/abs/2508.02583

作者：Keli Zhang, Ruichu Cai, Lujia Pan

【4】Contextual Graph Transformer: A Small Language Model for Enhanced Engineering Document Information Extraction
标题：上下文图Transformer：一种用于增强工程文档信息提取的小型语言模型
链接：https://arxiv.org/abs/2508.02532

作者：dy, Mayukha Pal

【5】I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2
标题：我没有嘴，我必须押韵：揭示LLaMA 3.2中的内部语音表示
链接：https://arxiv.org/abs/2508.02527

作者：llo, Arjun Khurana, Oliver McLaughlin

【6】AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs
标题：AnalogCoder-Pro：通过多模态LLM统一模拟电路生成和优化
链接：https://arxiv.org/abs/2508.02518

作者：Souradip Poddar, Sungyoung Lee, Guojin Chen, Mengkang Hu, Bei Yu, Ping Luo, David Z. Pan

【7】PoeTone: A Framework for Constrained Generation of Structured Chinese Songci with LLMs
标题：Poetone：用LLM约束生成结构化中国宋词的框架
链接：https://arxiv.org/abs/2508.02515

作者：Shuzhou Yuan, Michael Färber

【8】Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting
标题：用于端到端情感计算的多模态大型语言模型：使用生成知识推理进行基准测试和提升
链接：https://arxiv.org/abs/2508.02429

作者：uo, Jiesen Long, Zequn Li, Yunying Yang, Yuncheng Jiang, Sijie Mai

【9】Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs
标题：超越手动设计的修剪策略和二级性能预测：LLM的修剪框架
链接：https://arxiv.org/abs/2508.02381

作者： Yunhe Cui, Yongbin Qin

【10】Language Model Guided Reinforcement Learning in Quantitative Trading
标题：量化交易中的语言模型引导强化学习
链接：https://arxiv.org/abs/2508.02366

作者：anin, Vince Vella
备注：12 pages (4 pages appendix and references), 6 figures, preprint under review for FLLM 2025 conference

【11】MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models
标题：MicroMix：针对大型语言模型的高效混合精度量化，具有微缩放格式
链接：https://arxiv.org/abs/2508.02343

作者：iu, Haoqian Meng, Yilun Luo, Peng Zhang, Xindian Ma
备注：12 pages

【12】CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment
标题：CAPO：通过可验证的生成性信用分配来增强LLM推理
链接：https://arxiv.org/abs/2508.02298

作者：, Yunsheng Shi, Hongtao Tian, Ting Yao, Xiao Zhang
备注：Work in progress

【13】CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
标题：CO-RFT：通过分块离线强化学习对视觉-语言-动作模型进行高效微调
链接：https://arxiv.org/abs/2508.02219

作者：uang, Zhirui Fang, Tianle Zhang, Yihang Li, Lin Zhao, Chunhe Xia

【14】Balancing Information Accuracy and Response Timeliness in Networked LLMs
标题：平衡网络LLM中的信息准确性和响应及时性
链接：https://arxiv.org/abs/2508.02209

作者：kmen, Baturalp Buyukates, Melih Bastopcu

【15】Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
标题：种子扩散：具有高速推理的大规模扩散语言模型
链接：https://arxiv.org/abs/2508.02193

作者：ng, Zheng Zhang, Cheng Luo, Pengyang Gao, Fan Xia, Hao Luo, Zheng Li, Yuehang Yang, Hongli Yu, Xingwei Qu, Yuwei Fu, Jing Su, Ge Zhang, Wenhao Huang, Mingxuan Wang, Lin Yan, Xiaoying Jia, Jingjing Liu, Wei-Ying Ma, Ya-Qin Zhang, Yonghui Wu, Hao Zhou
备注：Demo is available at this https URL Project page is this https URL

【16】CAAD: Context-Aware Adaptive Decoding for Truthful Text Generation
标题：CAAD：用于真实文本生成的上下文感知自适应解码
链接：https://arxiv.org/abs/2508.02184

作者：en, Sunil Gupta, Hung Le

【17】Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models
标题：Amber Pruner：利用N：M激活稀疏性在大型语言模型中进行高效预填充
链接：https://arxiv.org/abs/2508.02128

作者：uwu Cai, Yanzhe Zhang, Yang Liu, Hao Chen, Pengcheng Xie, Sheng Chang, Yiwu Yao, Gongyi Wang

【18】The SMeL Test: A simple benchmark for media literacy in language models
标题：SMeL测试：语言模型中媒体素养的简单基准
链接：https://arxiv.org/abs/2508.02074

作者：dritz, Anat Kleiman

【19】MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
标题：MolReasoner：迈向分子LLM的有效且可解释的推理
链接：https://arxiv.org/abs/2508.02066

作者：Zhao, Sihang Li, Zixiang Lu, Zheng Cheng, Haitao Lin, Lirong Wu, Hanchen Xia, Hengxing Cai, Wentao Guo, Hongshuai Wang, Mingjun Xu, Siyu Zhu, Guolin Ke, Linfeng Zhang, Zhifeng Gao

【20】ProCut: LLM Prompt Compression via Attribution Estimation
标题：ProCut：通过归因估计的LLM提示压缩
链接：https://arxiv.org/abs/2508.02053

作者：u, Fengyi Li, Albert Chen, Xiaofeng Wang

【21】Prompting Large Language Models to Detect Dementia Family Caregivers
标题：推荐大型语言模型来检测痴呆症家庭护理人员
链接：https://arxiv.org/abs/2508.01999

作者： Biswas, Özlem Uzuner

【22】Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling
标题：通过部分奖励建模的早期拒绝加速LLM推理
链接：https://arxiv.org/abs/2508.01969

作者：eid Cheshmi, Azal Ahmad Khan, Xinran Wang, Zirui Liu, Ali Anwar

【23】Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
标题：重新审视重播和梯度对齐以连续预训练大型语言模型
链接：https://arxiv.org/abs/2508.01908

作者：Abbes, Gopeshh Subbaraj, Matthew Riemer, Nizar Islah, Benjamin Therien, Tsuguchika Tabaru, Hiroaki Kingetsu, Sarath Chandar, Irina Rish

【24】How Does Controllability Emerge In Language Models During Pretraining?
标题：预训练期间语言模型中如何出现可控性？
链接：https://arxiv.org/abs/2508.01892

作者：he, Xinyue Li, Eric Xing, Zhengzhong Liu, Qirong Ho

【25】AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization
标题：AGFT：用于实时LLM推理优化的自适应图形处理器
链接：https://arxiv.org/abs/2508.01744

作者：, Kunming Zhang, Guoming Tang

【26】MHARFedLLM: Multimodal Human Activity Recognition Using Federated Large Language Model
标题：MHARFedLLM：使用联邦大型语言模型的多模式人类活动识别
链接：https://arxiv.org/abs/2508.01701

作者：dyopadhyay, Rohit Basu, Tanmay Sen, Swagatam Das

【27】Innovative tokenisation of structured data for LLM training
标题：LLM训练的结构化数据的创新代币化
链接：https://arxiv.org/abs/2508.01685

作者：rim, Hani Ragab Hassen. Hadj Batatia

【28】EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models
标题：EAC-MoE：专家混合大型语言模型的专家选择感知压缩器
链接：https://arxiv.org/abs/2508.01625

作者：Chen, Yuantian Shao, Peisong Wang, Jian Cheng
备注：22 pages, 13 figures. ACL 2025

【29】Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention
标题：通过预览困难意识干预增强小型LLM中的数学推理
链接：https://arxiv.org/abs/2508.01604

作者：, JoyJiaoW
备注：7 pages, 1 table, accepted by SIM ICML@2025 Workshop

【30】End-to-End Personalization: Unifying Recommender Systems with Large Language Models
标题：端到端个性化：统一具有大型语言模型的推荐系统
链接：https://arxiv.org/abs/2508.01514

作者：rat, Tina Aminian, Sepideh Ahmadian, Luis Rueda
备注：Second Workshop on Generative AI for Recommender Systems and Personalization at the ACM Conference on Knowledge Discovery and Data Mining (GenAIRecP@KDD 2025)

【31】Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
标题：法学硕士的思想链推理是海市蜃楼吗？数据分布镜头
链接：https://arxiv.org/abs/2508.01191

作者：i Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu

【32】RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models
标题：RSPO：大型语言模型中Pass@k和Max@k收件箱的风险寻求策略优化
链接：https://arxiv.org/abs/2508.01174

作者：hang, Shenghao Gao, Yuzhong Hong, Haipeng Sun, Junwei Bao, Hongfei Jiang, Yang Song, Hong Dingqian, Hui Xiong

【33】DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs
标题：DBAIOps：使用知识图的推理LLM增强型数据库操作和维护系统
链接：https://arxiv.org/abs/2508.01136

作者： Peng Sun, Xuanhe Zhou, Qianglei Zang, Ji Xu, Tieying Zhang, Guoliang Li, Fan Wu
备注：DBAIOps supports 25 database systems and has been deployed in 20 real-world scenarios, covering domains like finance, energy, and healthcare. See website at: this https URL; See code at: this https URL

【34】FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
标题：FGBench：大型语言模型中功能组级分子属性推理的数据集和基准
链接：https://arxiv.org/abs/2508.01055

作者： Siru Ouyang, Xianrui Zhong, Jiawei Han, Huimin Zhao
备注：20 pages, 20 figures

【35】Optimal Scheduling Algorithms for LLM Inference: Theory and Practice
标题：LLM推理的最佳调度算法：理论与实践
链接：https://arxiv.org/abs/2508.01002

作者：i, Parikshit Hegde, Gustavo de Veciana

【36】VAULT: Vigilant Adversarial Updates via LLM-Driven Retrieval-Augmented Generation for NLI
标题：VASTRA：通过LLM-Driven Retrieval-Augmented Generation for NLI的警惕对抗更新
链接：https://arxiv.org/abs/2508.00965

作者：om, Ofir Cohen, Rami Puzis, Asaf Shabtai, Ofer Hadar

【37】From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
标题：从生成器到嵌入器：通过构建Zero-Shot鉴别嵌入模型来利用多模式LLM的先天能力
链接：https://arxiv.org/abs/2508.00955

作者：n Ju, Seong-Whan Lee

【38】OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction
标题：OKG-LLM：通过LLM将海洋知识图与观测数据对齐，以预测全球海表温度
链接：https://arxiv.org/abs/2508.00933

作者：ang, Jiaqi Wang, Jiannong Cao, Wengen Li, Jialun Zheng, Yangning Li, Chunyu Miao, Jihong Guan, Shuigeng Zhou, Philip S. Yu

【39】Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models
标题：超越基准：动态、自动和系统化的红色团队代理，用于值得信赖的医学语言模型
链接：https://arxiv.org/abs/2508.00923

作者：an, Bailiang Jian, Paul Hager, Yundi Zhang, Che Liu, Friedrike Jungmann, Hongwei Bran Li, Chenyu You, Junde Wu, Jiayuan Zhu, Fenglin Liu, Yuyuan Liu, Niklas Bubeck, Christian Wachinger, Chen (Cherise)Chen, Zhenyu Gong, Cheng Ouyang, Georgios Kaissis, Benedikt Wiestler, Daniel Rueckert

【40】Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
标题：通过推理长度估计对LLM API中隐藏令牌进行预测审计
链接：https://arxiv.org/abs/2508.00912

作者：g, Guoheng Sun, Yexiao He, Zheyu Shen, Bowei Tian, Ang Li

【41】Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling
标题：通过硬件不可知分析建模预测LLM推理性能
链接：https://arxiv.org/abs/2508.00904

作者：twari, Ashish Sirasao, Devleena Das
备注：10 pages, 9 figures

【42】AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
标题：AgentTTC：用于复杂任务中测试时计算最优扩展策略的大型语言模型代理
链接：https://arxiv.org/abs/2508.00890

作者：, Hui Liu, Zhenwei Dai, Jingying Zeng, Zhiwei Zhang, Zongyu Wu, Chen Luo, Zhen Li, Xianfeng Tang, Qi He, Suhang Wang
备注：Under review

【43】Contextual Phenotyping of Pediatric Sepsis Cohort Using Large Language Models
标题：使用大型语言模型对儿科脓毒症队列进行背景表型分析
链接：https://arxiv.org/abs/2505.09805

作者：gori, Ayush Gautam, Matthew O. Wiens, Vuong Nguyen, Nathan Kenya Mugisha, Jerome Kabakyenga, Niranjan Kissoon, John Mark Ansermino, Rishikesan Kamaleswaran
备注：11 pages, 2 Figures, 1 Table

Graph相关(图学习|图神经网络|图优化等)(16篇)

【1】Entity Representation Learning Through Onsite-Offsite Graph for Pinterset Ads
标题：通过Pinterset广告的现场-非现场图进行实体表示学习
链接：https://arxiv.org/abs/2508.02609

作者：n, Zhimeng Pan, Yang Tang, Jiarui Feng, Kungang Li, Chongyuan Xiang, Jiacheng Li, Runze Su, Siping Ji, Han Sun, Ling Leng, Prathibha Deshikachar

【2】Adaptive Riemannian Graph Neural Networks
标题：自适应Riemann图神经网络
链接：https://arxiv.org/abs/2508.02600

作者：ng, Tongxin Li, Chris Ding, Jicong Fan
备注：Under Review

【3】Federated Graph Unlearning
标题：联邦图取消学习
链接：https://arxiv.org/abs/2508.02485

作者：, Xunkai Li, Jiaqi Chao, Bowen Fan, Zhengyu Wu, Yinlin Zhu, Rong-Hua Li, Guoren Wang
备注：under review

【4】Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding
标题：学习进化：贝叶斯引导的连续知识图嵌入
链接：https://arxiv.org/abs/2508.02426

作者： Zhi Jin, Yuanpeng He, Dongming Jin, Yichi Zhang, Haoran Duan, Nyima Tash

【5】Graph Embedding in the Graph Fractional Fourier Transform Domain
标题：图分数傅里叶变换域中的图嵌入
链接：https://arxiv.org/abs/2508.02383

作者：Sheng, Zhichao Zhang, Wei Yao

【6】Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach
标题：通过嵌入重建的图去学习--范围-空间分解方法
链接：https://arxiv.org/abs/2508.02044

作者： Zipeng Liu, Xiaoyong Peng, Liyao Xiang
备注：15 pages

【7】From Binary to Continuous: Stochastic Re-Weighting for Robust Graph Explanation
标题：从二进制到连续：随机重新加权以实现稳健的图形解释
链接：https://arxiv.org/abs/2508.01925

作者：hen, Jingchao Ni, Hojat Allah Salehi, Xu Zheng, Dongsheng Luo

【8】GraphVSSM: Graph Variational State-Space Model for Probabilistic Spatiotemporal Inference of Dynamic Exposure and Vulnerability for Regional Disaster Resilience Assessment
标题：GraphVMSM：区域抗灾能力评估动态暴露和脆弱性概率时空推断的图变分状态空间模型
链接：https://arxiv.org/abs/2508.01310

作者：masaka, Christian Geiß, Emily So
备注：Non-peer-reviewed Preprint | Keywords: graph state-space model, building exposure, physical vulnerability, weak supervision, probabilistic model, disaster resilience, risk audit | Code: this https URL | Quezon City (Philippines) Dataset: this https URL | METEOR 2.5D Dataset, this https URL, this https URL | Khurushkul-Freetown Dataset: this https URL

【9】A graph neural network based on feature network for identifying influential nodes
标题：基于特征网络的图神经网络识别有影响力的节点
链接：https://arxiv.org/abs/2508.01278

作者：, Siyuan Yin, Yihang Wu, Xue Yue, Yue Liu

【10】Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features
标题：旧但好：重新照亮具有部分观察特征的图上的标签传播
链接：https://arxiv.org/abs/2508.01209

作者：n, Xin Liu, Yunhak Oh, Junseok Lee, Tianlong Chen, Tsuyoshi Murata, Chanyoung Park
备注：KDD 2025

【11】Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation
标题：利用文本边缘图表示弥合推荐中的评论稀疏性
链接：https://arxiv.org/abs/2508.01128

作者：g, Xutao Mao, Xuhui Zhan, Yuying Zhao, Bo Ni, Ryan A. Rossi, Nesreen K. Ahmed, Tyler Derr
备注：13 pages

【12】Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans
标题：结构化谱图学习用于3D胸部CT扫描异常分类
链接：https://arxiv.org/abs/2508.01045

作者：iazza, Carole Lazarus, Olivier Nempont, Loic Boussel
备注：Accepted for publication at MICCAI 2025 EMERGE Workshop

【13】FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graph
标题：FinKario：事件增强自动化金融知识图谱构建
链接：https://arxiv.org/abs/2508.00961

作者： Penglei Sun, Wanyun Zhou, Zikai Wei, Yongqi Zhang, Xiaowen Chu

【14】Multi-Community Spectral Clustering for Geometric Graphs
标题：几何图的多社区谱聚集
链接：https://arxiv.org/abs/2508.00893

作者：io Allem, Konstantin Avrachenkov, Carlos Hoppen, Hariprasad Manjunath, Lucas Siviero Sibemberg

【15】Multi-Grained Temporal-Spatial Graph Learning for Stable Traffic Flow Forecasting
标题：用于稳定交通流预测的多粒度时空图学习
链接：https://arxiv.org/abs/2508.00884

作者：n, Yuni Lai, Wai Lun Lo, Richard Tai-Chiu Hsung, Harris Sik-Ho Tsang, Xiaoyu Xue, Kai Zhou, Yulin Zhu

【16】GNN-ASE: Graph-Based Anomaly Detection and Severity Estimation in Three-Phase Induction Machines
标题：GNN-ASE：基于图形的三期感应电机异常检测和严重性估计
链接：https://arxiv.org/abs/2508.00879

作者：llah Bentrad, Adel Ghoggal, Tahar Bahi, Abderaouf Bahi

Transformer(12篇)

【1】DeepKoopFormer: A Koopman Enhanced Transformer Based Architecture for Time Series Forecasting
标题：DeepKoopFormer：用于时间序列预测的基于Koopman增强型Transformer的架构
链接：https://arxiv.org/abs/2508.02616

作者：tani, Mohammad Khosravi, Masoud Barati

【2】HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis
标题：HGTS-Former：用于多元时间序列分析的分层超图Transformer
链接：https://arxiv.org/abs/2508.02411

作者：, Hao Si, Fan Zhang, Xiaoya Zhou, Dengdi Sun, Wanli Lyu, Qingquan Yang, Jin Tang

【3】Convolutions are Competitive with Transformers for Encrypted Traffic Classification with Pre-training
标题：卷积在预训练的加密流量分类方面与Transformers竞争
链接：https://arxiv.org/abs/2508.02001

作者：Lin, Weiyao Zhang, Tianyu Zuo, Chao Zha, Yilong Jiang, Ruiqi Meng, Haitong Luo, Xuying Meng, Yujun Zhang
备注：Under review

【4】Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation
标题：迈向高效峰值Transformer：Synasse修剪满足基于学习的协同补偿
链接：https://arxiv.org/abs/2508.01992

作者：n, Wuque Cai, Duo Chen, Shifeng Mao, Jiayi He, Zhenxing Wang, Dezhong Yao, Daqing Guo

【5】LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning
标题：LethheViT：通过注意力引导对比学习对视觉变形者进行选择性机器取消学习
链接：https://arxiv.org/abs/2508.01569

作者：g, Tian Zhang, Jingling Yuan, Yuze Wang, Chuang Hu

【6】FluidFormer: Transformer with Continuous Convolution for Particle-based Fluid Simulation
标题：FluidFormer：用于基于颗粒的流体模拟的连续卷积Transformer
链接：https://arxiv.org/abs/2508.01537

作者：ng, Yu Chen, Shuai Zheng

【7】HT-Transformer: Event Sequences Classification by Accumulating Prefix Information with History Tokens
标题：HT-Transformer：通过使用历史令牌积累后缀信息进行事件序列分类
链接：https://arxiv.org/abs/2508.01474

作者：ukhin, Andrey Savchenko

【8】Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search
标题：具有Transformer神经网络和推测性射束搜索的快速且可扩展的逆合成规划
链接：https://arxiv.org/abs/2508.01459

作者：ndronov, Natalia Andronova, Michael Wand, Jürgen Schmidhuber, Djork-Arné Clevert

【9】CPformer -- Concept and Physics enhanced Transformer for Time Series Forecasting
标题：CPformer --概念和物理增强型时间序列预测Transformer
链接：https://arxiv.org/abs/2508.01407

作者：a, Junbin Gao, Minh-Ngoc Tran

【10】Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and Practice
标题：伪随机数生成中的Transformer：理论与实践的双重视角
链接：https://arxiv.org/abs/2508.01134

作者：ingshu Zeng
备注：27 pages, 4 figures

【11】Filtering with Self-Attention and Storing with MLP: One-Layer Transformers Can Provably Acquire and Extract Knowledge
标题：自我注意力过滤并MLP存储：单层Transformer可以证明获取和提取知识
链接：https://arxiv.org/abs/2508.00901

作者：u, Kexin Chen

【12】A Residual Guided strategy with Generative Adversarial Networks in training Physics-Informed Transformer Networks
标题：使用生成对抗网络的剩余引导策略训练物理信息Transformer网络
链接：https://arxiv.org/abs/2508.00855

作者：ang, Feifan Zhang, Weidong Tang, Lei Shi, Tailai Chen

GAN|对抗|攻击|生成相关(10篇)

【1】CSI Obfuscation: Single-Antenna Transmitters Can Not Hide from Adversarial Multi-Antenna Radio Localization Systems
标题：SI混淆：单天线发射机无法隐藏对抗性多天线无线电定位系统
链接：https://arxiv.org/abs/2508.02553

作者：tephan, Florian Euchner, Stephan ten Brink

【2】Toward Using Machine Learning as a Shape Quality Metric for Liver Point Cloud Generation
标题：迈向使用机器学习作为肝脏点云生成的形状质量指标
链接：https://arxiv.org/abs/2508.02482

作者： Nguyen, Gaeun Oh, Ho-min Park, Francesca Tozzi, Wouter Willaert, Joris Vankerschaver, Niki Rashidian, Wesley De Neve

【3】Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation
标题：Uni-lay：将人类反馈整合到统一布局生成和评估中
链接：https://arxiv.org/abs/2508.02374

作者：Yanyin Chen, Wei Feng, Jiahao Fan, Fengheng Li, Zheng Zhang, Jingjing Lv, Junjie Shen, Ching Law, Jian Liang
备注：Accepted to ACM MM 2025

【4】An Evolving Scenario Generation Method based on Dual-modal Driver Model Trained by Multi-Agent Reinforcement Learning
标题：基于多智能体强化学习训练的双模式驾驶员模型的进化场景生成方法
链接：https://arxiv.org/abs/2508.02027

作者：Wu, Junyi Chen, Shaolingfeng Ye, Wei Jiang, Yong Shen
备注：16 pages, 17 figures

【5】Controllable and Stealthy Shilling Attacks via Dispersive Latent Diffusion
标题：通过分散潜在扩散进行可控且隐形的先令攻击
链接：https://arxiv.org/abs/2508.01987

作者：iao, Wei Yuan, Junliang Yu, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin

【6】Agent-Based Feature Generation from Clinical Notes for Outcome Prediction
标题：基于Agent的临床病历特征生成及其预后预测
链接：https://arxiv.org/abs/2508.01956

作者：g, Jacqueline Jil Vallon, Neil Panjwani, Xi Ling, Sushmita Vij, Sandy Srinivas, John Leppert, Mark K. Buyyounouski, Mohsen Bayati

【7】Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinity and Auxiliary Regularization
标题：通过自适应邻近和辅助正规化实现不平衡稳健且采样高效的连续条件GAN
链接：https://arxiv.org/abs/2508.01725

作者： Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang

【8】Benchmarking Adversarial Patch Selection and Location
标题：对抗补丁选择和位置基准
链接：https://arxiv.org/abs/2508.01676

作者：i, Avi Mendlson, Moshe Kimhi

【9】TCDiff: Triplex Cascaded Diffusion for High-fidelity Multimodal EHRs Generation with Incomplete Clinical Data
标题：TCDiff：用于在不完整临床数据下产生高保真多模式EHR的三重级联扩散
链接：https://arxiv.org/abs/2508.01615

作者：an, Chenxi Li, Yu Huang, Dexuan Xu, Jiaqi Zhu, Zhongyan Chai, Huamin Zhang

【10】Deep Kernel Bayesian Optimisation for Closed-Loop Electrode Microstructure Design with User-Defined Properties based on GANs
标题：基于GAN的具有用户自定义属性的闭环电极微结构设计深核Bayesian优化
链接：https://arxiv.org/abs/2508.00833

作者：yon-Lombardo, Ehecatl A. del Rio-Chanona, Catalina A. Pino-Munoz, Nigel P. Brandon
备注：This work is part of the PhD thesis that can be found in the Imperial College archives: this https URL

半/弱/无/有监督|不确定性|主动学习(15篇)

【1】Dynamic Feature Selection based on Rule-based Learning for Explainable Classification with Uncertainty Quantification
标题：基于基于规则学习的动态特征选择，用于不确定性量化的可解释分类
链接：https://arxiv.org/abs/2508.02566

作者：manal-Idocin, Raquel Fernandez-Peralta, Javier Andreu-Perez

【2】Clinical Expert Uncertainty Guided Generalized Label Smoothing for Medical Noisy Label Learning
标题：临床专家不确定性引导的广义标签平滑用于医疗噪音标签学习
链接：https://arxiv.org/abs/2508.02495

作者：ng, Lin Gu, Liangchen Liu, Yingke Chen, Bingyang Wang, Jin Yan, Yingying Zhu

【3】Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning
标题：通过自信元学习实现真正的无监督异常检测
链接：https://arxiv.org/abs/2508.02293

作者：Aqeel, Shakiba Sharifi, Marco Cristani, Francesco Setti
备注：Accepted to ieee/cvf international conference on computer vision (ICCV2025)

【4】Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning
标题：多源无数据监督迁移学习的模型回收框架
链接：https://arxiv.org/abs/2508.02039

作者：g, Ricardo Henao

【5】Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
标题：利用无监督学习将表示空间分解为可解释子空间
链接：https://arxiv.org/abs/2508.01916

作者：uang, Michael Hahn

【6】Unsupervised Learning for the Elementary Shortest Path Problem
标题：基本最短路径问题的无监督学习
链接：https://arxiv.org/abs/2508.01557

作者：en, Xinyuan Zhang, Xinwu Qian

【7】Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport
标题：具有最佳传输的音调估计的翻译等变自监督学习
链接：https://arxiv.org/abs/2508.01493

作者：Torres, Alain Riou, Gaël Richard, Geoffroy Peeters
备注：Extended Abstracts for the Late-Breaking Demo Session of the 26th International Society for Music Information Retrieval Conference

【8】PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
标题：PESTO：具有自监督转置等变目标的实时音调估计
链接：https://arxiv.org/abs/2508.01488

作者：u, Bernardo Torres, Ben Hayes, Stefan Lattner, Gaëtan Hadjeres, Gaël Richard, Geoffroy Peeters
备注：Accepted to the Transactions of the International Society for Music Information Retrieval

【9】Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning
标题：软分离和蒸馏：迈向联邦无监督学习的全球统一性
链接：https://arxiv.org/abs/2508.01251

作者：h Fang, Hsuan-Tien Lin, Irwin King, Yifei Zhang
备注：Published at ICCV 2025

【10】Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasing
标题：通过模糊性不确定性校准和视视去偏置增强多视图开放集学习
链接：https://arxiv.org/abs/2508.01227

作者：g, Zhiyong Xu, Lan Du, Shide Du, Zhiling Cai, Shiping Wang

【11】CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning
标题：CalibMatch：用于改善安全半监督学习的自适应校准
链接：https://arxiv.org/abs/2508.00922

作者：e, Seoung Bum Kim, Hyungrok Do

【12】TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
标题：TESPEC：活动摄像机的临时增强自我监督预训练
链接：https://arxiv.org/abs/2508.00913

作者：Mohammadi, Ziyi Wu, Igor Gilitschenski
备注：Accepted at IEEE/CVF International Conference on Computer Vision (ICCV) 2025

【13】NeuCoReClass AD: Redefining Self-Supervised Time Series Anomaly Detection
标题：NeuCoReClass AD：重新定义自我监督时间序列异常检测
链接：https://arxiv.org/abs/2508.00909

作者：chez-Ferrera, Usue Mori, Borja Calvo, Jose A. Lozano

【14】Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling
标题：通过Post-StoNet建模对大规模深度网络进行不确定性量化
链接：https://arxiv.org/abs/2508.01217

作者：Faming Liang

【15】A General Approach to Visualizing Uncertainty in Statistical Graphics
标题：统计图形中不确定性可视化的一般方法
链接：https://arxiv.org/abs/2508.00937

作者：Petek, David Nabergoj, Erik Štrumbelj

迁移|Zero/Few/One-Shot|自适应(7篇)

【1】Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules
标题：参数高效的路由微调：专家混合需要混合适应模块
链接：https://arxiv.org/abs/2508.02587

作者：, Yunpu Ma, Yuetian Lu, Shuo Chen, Zifeng Ding, Volker Tresp
备注：This paper is a preprint under review. arXiv admin note: text overlap with arXiv:2411.08212

【2】An Efficient and Adaptive Next Edit Suggestion Framework with Zero Human Instructions in IDEs
标题：IDE中零人工指令的高效且自适应的下一个编辑建议框架
链接：https://arxiv.org/abs/2508.02473

作者：hen, Siyang Xiao, Xianying Zhu, Junhong Xie, Ming Liang, Dajun Chen, Wei Jiang, Yong Li, Peng Di
备注：13 pages

【3】Multi-Operator Few-Shot Learning for Generalization Across PDE Families
标题：多操作员Few-Shot学习，用于跨DTE系列的推广
链接：https://arxiv.org/abs/2508.01211

作者：Shandian Zhe

【4】MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management
标题：MARS：用于风险感知多代理投资组合管理的元自适应强化学习框架
链接：https://arxiv.org/abs/2508.01173

作者：n, Jing Li, Guiling Wang

【5】COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy Learning
标题：COLLAGE：用于增强政策学习的自适应基于融合的检索
链接：https://arxiv.org/abs/2508.01131

作者：umar, Shivin Dass, Georgios Pavlakos, Roberto Martín-Martín
备注：Accepted at the Conference on Robot Learning (CoRL), 2025. Project page: this https URL

【6】Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies
标题：集中式自适应采样用于独立多代理策略的可靠联合训练
链接：https://arxiv.org/abs/2508.01049

作者：E. Corrado, Josiah P. Hanna

【7】Small sample-based adaptive text classification through iterative and contrastive description refinement
标题：通过迭代和对比描述细化实现基于小样本的自适应文本分类
链接：https://arxiv.org/abs/2508.00957

作者：eev, Udayaadithya Avadhanam, Harshula Tulapurkar, SaiBarath Sundar

强化学习(9篇)

【1】Computationally efficient Gauss-Newton reinforcement learning for model predictive control
标题：用于模型预测控制的计算高效高斯-牛顿强化学习
链接：https://arxiv.org/abs/2508.02441

作者：dner, Sebastien Gros, Sergio Lucia
备注：14 pages, 8 figures, submitted to Elsevier

【2】Emergence of Fair Leaders via Mediators in Multi-Agent Reinforcement Learning
标题：多智能体强化学习中通过调解器出现公平领导者
链接：https://arxiv.org/abs/2508.02421

作者：dwadmath, Setareh Maghsudi
备注：Accepted to ECAI 2025

【3】Multi-Policy Pareto Front Tracking Based Online and Offline Multi-Objective Reinforcement Learning
标题：基于多策略帕累托前沿跟踪的在线和线下多目标强化学习
链接：https://arxiv.org/abs/2508.02217

作者：, Yueling Che, Kaichen Liu, Jian Li, Junmei Yao
备注：24 pages, 10 figures, conference paper

【4】PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
标题：PIGDreamer：用于安全部分可观察强化学习的特权信息引导世界模型
链接：https://arxiv.org/abs/2508.02159

作者：uang, Jiaqi Wang, Yang Li, Chunhe Xia, Tianle Zhang, Kaige Zhang
备注：ICML 2025

【5】Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
标题：通过最大似然估计的实例相关连续时间强化学习
链接：https://arxiv.org/abs/2508.02103

作者：o, Yue Yu, Ruhan Wang, Chunfeng Huang, Dongruo Zhou
备注：32 pages, 3 figures, 1 table. The first two authors contributed equally

【6】CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
标题：CRINN：用于大约最近邻居搜索的对比强化学习
链接：https://arxiv.org/abs/2508.02091

作者：, Xiaofei Sun, Albert Wang, Chris Shum, Jiwei Li
备注：Preprint Version

【7】Augmented Reinforcement Learning Framework For Enhancing Decision-Making In Machine Learning Models Using External Agents
标题：使用外部代理增强机器学习模型决策的增强强化学习框架
链接：https://arxiv.org/abs/2508.01612

作者：umar Singh
备注：Master's thesis, 274 pages, 8 Tables, 73 figures

【8】MoRe-ERL: Learning Motion Residuals using Episodic Reinforcement Learning
标题：MoRe-ERL：使用情景强化学习运动残余
链接：https://arxiv.org/abs/2508.01409

作者： Hongyi Zhou, Ge Li, Yucheng Tang, Weiran Liao, Björn Hein, Tamim Asfour, Rudolf Lioutikov

【9】Is Exploration or Optimization the Problem for Deep Reinforcement Learning?
标题：探索还是优化是深度强化学习的问题？
链接：https://arxiv.org/abs/2508.01329

作者：eth

元学习(2篇)

【1】HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
标题：HealthFlow：一个具有自主医疗保健研究Meta规划的自进化人工智能代理
链接：https://arxiv.org/abs/2508.02621

作者：hu, Yifan Qi, Zixiang Wang, Lei Gu, Dehao Sui, Haoran Hu, Xichen Zhang, Ziyi He, Liantao Ma, Lequan Yu
备注：Code: this https URL

【2】TensoMeta-VQC: A Tensor-Train-Guided Meta-Learning Framework for Robust and Scalable Variational Quantum Computing
标题：TensoMeta-VQC：一个用于稳健且可扩展的变分量子计算的张量训练引导元学习框架
链接：https://arxiv.org/abs/2508.01116

作者：hao-Han Yang, Pin-Yu Chen, Min-Hsiu Hsieh
备注：In submission

符号|符号学习(1篇)

【1】A Compression Based Classification Framework Using Symbolic Dynamics of Chaotic Maps
标题：使用混乱地图符号动力学的基于压缩的分类框架
链接：https://arxiv.org/abs/2508.02330

作者：k, Harikrishnan N B
备注：4 figures, 3 tables

医学相关(11篇)

【1】AutoML-Med: A Framework for Automated Machine Learning in Medical Tabular Data
标题：AutoML-Med：医学表格数据中的自动机器学习框架
链接：https://arxiv.org/abs/2508.02625

作者：Francia, Maurizio Leone, Giorgio Leonardi, Stefania Montani, Marzio Pennisi, Manuel Striani, Sandra D'Alfonso
备注：8 pages, preprint for conference

【2】Automated SNOMED CT Concept Annotation in Clinical Text Using Bi-GRU Neural Networks
标题：使用Bi-GRU神经网络在临床文本中自动标注SNOMED CT概念
链接：https://arxiv.org/abs/2508.02556

作者：, Pratik Devkota, Somya Mohanty, Prashanti Manda

【3】Whole-body Representation Learning For Competing Preclinical Disease Risk Assessment
标题：竞争性临床前疾病风险评估的全身代表学习
链接：https://arxiv.org/abs/2508.02307

作者：eletkov, Sophie Starck, Ayhan Can Erdur, Yundi Zhang, Daniel Rueckert, Rickmer Braren

【4】Do Edges Matter? Investigating Edge-Enhanced Pre-Training for Medical Image Segmentation
标题：边缘重要吗？研究医学图像分割的边缘增强预训练
链接：https://arxiv.org/abs/2508.02281

作者：, Lars Böcking, Simeon Allmendinger, Leopold Müller, Niklas Kühl
备注：11 pages, 5 figures, Third International Workshop on Data Engineering in Medical Imaging (DEMI 2025)

【5】BSL: A Unified and Generalizable Multitask Learning Platform for Virtual Drug Discovery from Design to Synthesis
标题：BSL：一个统一且可扩展的多任务学习平台，用于从设计到合成的虚拟药物发现
链接：https://arxiv.org/abs/2508.01195

作者：hennan Wu, Yida Xiong, Hongzhi Zhang, Longtao Hu, Zhonglie Liu, Junqi Zeng, Wenjie Wu, Mukun Chen, Jiameng Chen, Wenbin Hu

【6】Masked Omics Modeling for Multimodal Representation Learning across Histopathology and Molecular Profiles
标题：跨组织学和分子谱的多模式表示学习的掩蔽组学建模
链接：https://arxiv.org/abs/2508.00969

作者：inet, Ahmad Berjaoui, Elizabeth Cohen-Jonathan Moyal

【7】Rethinking Multimodality: Optimizing Multimodal Deep Learning for Biomedical Signal Classification
标题：重新思考多模式：优化多模式深度学习以实现生物医学信号分类
链接：https://arxiv.org/abs/2508.00963

作者：ladunni, Alex Wong

【8】Cooperative effects in feature importance of individual patterns: application to air pollutants and Alzheimer disease
标题：个体模式特征重要性的协同效应：应用于空气污染物和阿尔茨海默病
链接：https://arxiv.org/abs/2508.00930

作者：ro-Ortega, A. Fania, A. Lacalamita, R. Bellotti, A. Monaco, S. Stramaglia

【9】FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA
标题：FairFedMed：与FairLoRA一起对联邦医学成像中的群体公平性进行基准
链接：https://arxiv.org/abs/2508.00873

作者：i, Congcong Wen, Yu Tian, Min Shi, Yan Luo, Hao Huang, Yi Fang, Mengyu Wang
备注：11 pages, 5 figures, 8 tables

【10】Less is More: AMBER-AFNO -- a New Benchmark for Lightweight 3D Medical Image Segmentation
标题：少即是多：AMBER-AFNO --轻量级3D医学图像分割的新基准
链接：https://arxiv.org/abs/2508.01941

作者：si, Semanto Mondal, Rajib Chandra Ghosh, Massimo Brescia, Giuseppe Longo

【11】Contrastive Multi-Task Learning with Solvent-Aware Augmentation for Drug Discovery
标题：药物发现的对比多任务学习和溶剂感知增强
链接：https://arxiv.org/abs/2508.01799

作者： Hexiao Ding, Hongzhao Chen, Yufeng Jiang, Ng Nga Chun, Gerald W.Y. Cheng, Zongxi Li, Jing Cai, Liang-ting Lin, Jung Sun Yoo
备注：10 pages, 4 figures

蒸馏|知识提取(4篇)

【1】Large-Scale Model Enabled Semantic Communication Based on Robust Knowledge Distillation
标题：基于鲁棒知识提取的大规模模型语义通信
链接：https://arxiv.org/abs/2508.02148

作者：Ing, Caili Guo, Yang Yang, Zhongtian Du, Walid Saad
备注：13 pages, 8 figures, 3 tables

【2】OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
标题：OccamGMS：将视觉模型提炼为1%参数以进行时间序列预测
链接：https://arxiv.org/abs/2508.01727

作者：, Siru Zhong, Weilin Ruan, Qingxiang Liu, Qingsong Wen, Hui Xiong, Yuxuan Liang

【3】From SHAP to Rules: Distilling Expert Knowledge from Post-hoc Model Explanations in Time Series Classification
标题：从SHAP到规则：从时间序列分类中的事后模型解释中提取专家知识
链接：https://arxiv.org/abs/2508.01687

作者：zolewski, Szymon Bobek, Grzegorz J. Nalepa

【4】DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
标题：DisTaC：通过蒸馏调节任务载体以实现稳健模型合并
链接：https://arxiv.org/abs/2508.01148

作者：shida, Yuji Naraki, Takafumi Horie, Ryotaro Shimizu, Hiroki Naganuma

推荐(1篇)

【1】Addressing Cold Start For next-article Recommendation
标题：解决下一篇文章推荐的冷启动问题
链接：https://arxiv.org/abs/2508.01036

作者：hary, Nathan Jorgenson, Trenton Marple

聚类(1篇)

【1】Dynamic Clustering for Personalized Federated Learning on Heterogeneous Edge Devices
标题：用于异类边缘设备上个性化联邦学习的动态集群
链接：https://arxiv.org/abs/2508.01580

作者：u, Junzhe Huang, Fang He, Guohong Cao

超分辨率|去噪|去模糊|去雾(1篇)

【1】Why Heuristic Weighting Works: A Theoretical Analysis of Denoising Score Matching
标题：启发式加权为何有效：去噪得分匹配的理论分析
链接：https://arxiv.org/abs/2508.01597

作者：ng, Rhys Newbury, Xinyang Zhang, Tin Tran, Dana Kulic, Michael Burke

自动驾驶|车辆|车道检测等(4篇)

【1】Actionable Counterfactual Explanations Using Bayesian Networks and Path Planning with Applications to Environmental Quality Improvement
标题：使用Bayesian网络和路径规划的可操作反事实解释及其在环境质量改善中的应用
链接：https://arxiv.org/abs/2508.02634

作者：alero-Leal, Pedro Larrañaga, Concha Bielza

【2】Real-Time Conflict Prediction for Large Truck Merging in Mixed Traffic at Work Zone Lane Closures
标题：作业区车道封闭条件下混合交通中大型货车并入的实时冲突预测
链接：https://arxiv.org/abs/2508.02109

作者：n, Abdullah Al Mamun, Gurcan Comert, Debbie Aisiana Indah, Judith Mwakalonge, Amy W. Apon, Mashrur Chowdhury
备注：This work has been submitted to the Transportation Research Record: Journal of the Transportation Research Board for possible publication

【3】A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles
标题：互联自动驾驶汽车中的深度多任务学习综述
链接：https://arxiv.org/abs/2508.00917

作者：ang, Farhad Pourpanah, Q. M. Jonathan Wu, Ning Zhang
备注：arXiv admin note: text overlap with arXiv:2303.01788, arXiv:2304.01168 by other authors

【4】A Dynamic, Context-Aware Framework for Risky Driving Prediction Using Naturalistic Data
标题：使用自然数据进行风险驾驶预测的动态、上下文感知框架
链接：https://arxiv.org/abs/2508.00888

作者：ein Kalantari, Eleonora Papadimitriou, Amir Pooyan Afghari
备注：32 pages

联邦学习|隐私保护|加密(8篇)

【1】Communication and Computation Efficient Split Federated Learning in O-RAN
标题：O-RAN中的通信和计算高效分离联邦学习
链接：https://arxiv.org/abs/2508.02534

作者：Gu, Chaoqun You, Bangbang Ren, Deke Guo

【2】ASMR: Angular Support for Malfunctioning Client Resilience in Federated Learning
标题：ASMR：对联邦学习中故障客户复原力的角度支持
链接：https://arxiv.org/abs/2508.02414

作者：stantin, Moritz Fuchs, Anirban Mukhopadhyay
备注：None

【3】FedLAD: A Linear Algebra Based Data Poisoning Defence for Federated Learning
标题：FedRAD：基于线性代数的联邦学习数据中毒防御
链接：https://arxiv.org/abs/2508.02136

作者： Hai Dong, Nasrin Sohrabi, Zahir Tari

【4】Mitigating Persistent Client Dropout in Asynchronous Decentralized Federated Learning
标题：缓解非集中式联邦学习中的持续客户端退出
链接：https://arxiv.org/abs/2508.01807

作者：ępka, Nicholas Gisolfi, Kacper Trębacz, Artur Dubrawski
备注：Presented on FedKDD Workshop at KDD 2025

【5】Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design
标题：通过联合数据、计算和通信设计实现边缘实时视觉的节能联邦学习
链接：https://arxiv.org/abs/2508.01745

作者： Hou, Jingjing Wang, Fangming Guan, Jun Du, Chunxiao Jiang, Yong Ren

【6】Asynchronous Federated Learning with non-convex client objective functions and heterogeneous dataset
标题：具有非凸客户端目标函数和异类数据集的同步联邦学习
链接：https://arxiv.org/abs/2508.01675

作者：tani, Raffaele Iervolino

【7】Boosting Generalization Performance in Model-Heterogeneous Federated Learning Using Variational Transposed Convolution
标题：使用变分转置卷积提高模型异类联邦学习中的概括性能
链接：https://arxiv.org/abs/2508.01669

作者： Hai Dong, A.K. Qin

【8】Convergence Analysis of Aggregation-Broadcast in LoRA-enabled Federated Learning
标题：LoRA联邦学习中聚集广播的收敛性分析
链接：https://arxiv.org/abs/2508.01348

作者： Shuaijun Chen, Omid Tavallaie, Nguyen Tran, Shuhuang Xiang, Albert Zomaya

推理|分析|理解|解释(23篇)

【1】EHSAN: Leveraging ChatGPT in a Hybrid Framework for Arabic Aspect-Based Sentiment Analysis in Healthcare
标题：EHSAN：在混合框架中利用ChatGPT进行基于阿拉伯语的医疗保健情绪分析
链接：https://arxiv.org/abs/2508.02574

作者：oudi, Ellis Solaiman

【2】Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application
标题：神经成像的可解释人工智能方法：常用工具的系统性故障、特定领域验证的需要以及安全应用的建议
链接：https://arxiv.org/abs/2508.02560

作者： Siegel, James H. Cole, Mohamad Habes, Stefan Haufe, Kerstin Ritter, Marc-André Schulz

【3】Detecting COPD Through Speech Analysis: A Dataset of Danish Speech and Machine Learning Approach
标题：通过语音分析检测COPD：丹麦语音和机器学习方法的数据集
链接：https://arxiv.org/abs/2508.02354

作者：ey-Olsen, Rasmus Hvass Olesen, Tobias Oliver Eberhard, Andreas Triantafyllopoulos, Björn Schuller, Ilhan Aslan

【4】CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
标题：CAMERA：基于微观专家冗余分析的MoE模型多矩阵联合压缩
链接：https://arxiv.org/abs/2508.02322

作者：Xu, Xu Han, Yuanchi Zhang, Yixuan Wang, Yijun Liu, Shiyu Ji, Qingfu Zhu, Wanxiang Che
备注：16 pages, 9 figures, 7 tables

【5】An Enhanced Focal Loss Function to Mitigate Class Imbalance in Auto Insurance Fraud Detection with Explainable AI
标题：增强的焦点损失函数，利用可解释人工智能缓解汽车保险欺诈检测中的阶级失衡
链接：https://arxiv.org/abs/2508.02283

作者：oabang, Samuel Asante Gyamerah
备注：28 pages, 4 figures, 2 tables

【6】Understanding Learning Dynamics Through Structured Representations
标题：通过结构化表示理解学习动态
链接：https://arxiv.org/abs/2508.02126

作者：ooroo, Thomas Engel

【7】Understanding the Essence: Delving into Annotator Prototype Learning for Multi-Class Annotation Aggregation
标题：理解本质：深入研究用于多类注释聚合的注释器原型学习
链接：https://arxiv.org/abs/2508.02123

作者：Jun Feng, Shenyu Zhang

【8】A Comprehensive Analysis of Evolving Permission Usage in Android Apps: Trends, Threats, and Ecosystem Insights
标题：Android应用程序中不断变化的权限使用情况的全面分析：趋势、威胁和生态系统见解
链接：https://arxiv.org/abs/2508.02008

作者：oon, Trung Cuong Dang, Ahod Alghuried, Abdulaziz Alghamdi, Soohyeon Choi, Manar Mohaisen, An Wang, Saeed Salem, David Mohaisen
备注：16 pages, 6 figures, 14 tables. In submission to Journal of Cybersecurity and Privacy

【9】Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements
标题：神经预测控制协调离散和连续时间模型进行时间序列分析，并改进控制理论
链接：https://arxiv.org/abs/2508.01833

作者：, Muhao Guo, Yang Weng, Hanghang Tong
备注：14 pages, submitted to ACM SIGKDD Conference on Knowledge Discovery and Data Mining

【10】Semantically-Guided Inference for Conditional Diffusion Models: Enhancing Covariate Consistency in Time Series Forecasting
标题：条件扩散模型的语义引导推理：增强时间序列预测中的协变量一致性
链接：https://arxiv.org/abs/2508.01761

作者： Hanyang Meng, Zeyang Zhang, Jielong Yang

【11】Privacy-Preserving Inference for Quantized BERT Models
标题：量化BERT模型的隐私保护推理
链接：https://arxiv.org/abs/2508.01636

作者：u, Bingsheng Zhang, Lekun Peng, Bowen Zheng, Lichun Li, Kui Ren

【12】FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models
标题：Flash DID：低级别模型的流媒体高效推理
链接：https://arxiv.org/abs/2508.01506

作者：ao, Yixiao Wang, Qinsi Wang, Ting Jiang, Zhixu Du, Hancheng Ye, Danyang Zhuo, Yiran Chen, Hai Li
备注：Technical Report

【13】AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
标题：AgentArmor：对Agent DeliverTrace执行程序分析以防止即时注入
链接：https://arxiv.org/abs/2508.01249

作者：ng, Yang Liu, Yunfei Lu, Yifeng Cai, Hongbo Chen, Qingyou Yang, Jie Zhang, Jue Hong, Ye Wu

【14】Explaining GNN Explanations with Edge Gradients
标题：用Edge继承人解释GNN解释
链接：https://arxiv.org/abs/2508.01048

作者： Akbar Rafiey, Gal Mishne, Yusu Wang
备注：KDD 2025

【15】Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis
标题：使用语义分析进行多跳问题解答的知识编辑
链接：https://arxiv.org/abs/2508.00914

作者：imon, Rickard Ewetz
备注：14 pages, 15 figures, pre-print of paper accepted to IJCAI 2025

【16】Cross-Process Defect Attribution using Potential Loss Analysis
标题：使用潜在损失分析的跨流程缺陷归因
链接：https://arxiv.org/abs/2508.00895

作者：Idé, Kohei Miyaguchi
备注：arXiv admin note: text overlap with arXiv:2507.20357

【17】Towards Actionable Pedagogical Feedback: A Multi-Perspective Analysis of Mathematics Teaching and Tutoring Dialogue
标题：迈向可操作的教学反馈：数学教学与辅导对话的多视角分析
链接：https://arxiv.org/abs/2505.07161

作者：Naim, Jie Cao, Fareen Tasneem, Jennifer Jacobs, Brent Milne, James Martin, Tamara Sumner
备注：Accepted to EDM'2025

【18】Enhancing Talk Moves Analysis in Mathematics Tutoring through Classroom Teaching Discourse
标题：通过课堂教学话语加强数学教学中的言语动作分析
链接：https://arxiv.org/abs/2412.13395

作者：Abhijit Suresh, Jennifer Jacobs, Charis Clevenger, Amanda Howard, Chelsea Brown, Brent Milne, Tom Fischaber, Tamara Sumner, James H. Martin
备注：Accepted to COLING'2025

【19】Trustworthy scientific inference for inverse problems with generative models
标题：使用生成式模型对逆问题进行值得信赖的科学推断
链接：https://arxiv.org/abs/2508.02602

作者：zon, Luca Masserano, Joshua D. Ingram, Alex Shen, Antonio Carlos Herling Ribeiro Junior, Tommaso Dorigo, Michele Doro, Joshua S. Speagle, Rafael Izbicki, Ann B. Lee

【20】Structure Maintained Representation Learning Neural Network for Causal Inference
标题：用于因果推理的结构保持表示学习神经网络
链接：https://arxiv.org/abs/2508.01865

作者： Wenbin Lu, Yi-Hui Zhou

【21】Fast Gaussian process inference by exact Matérn kernel decomposition
标题：通过精确Matérn核分解快速高斯过程推断
链接：https://arxiv.org/abs/2508.01864

作者：angrené, Xavier Warin, Pierre Gruet
备注：31 pages, 1 figure

【22】Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis
链接：https://arxiv.org/abs/2508.01341

作者：ttersson, Connor T. Jerzak, Adel Daoud
备注：31 pages

【23】Flow IV: Counterfactual Inference In Nonseparable Outcome Models Using Instrumental Variables
标题：流程四：使用工具变量的不可分离结果模型中的反事实推理
链接：https://arxiv.org/abs/2508.01321

作者：n, Jose M. Peña, Adel Daoud

检测相关(8篇)

【1】Robust Detection of Planted Subgraphs in Semi-Random Models
标题：半随机模型中植入子图的鲁棒检测
链接：https://arxiv.org/abs/2508.02158

作者：lech, Wasim Huleihel
备注：32 pages

【2】Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach
标题：通过线性化方法基于核的稀疏可加性非线性模型结构检测
链接：https://arxiv.org/abs/2508.01453

作者：rahimkhani, John Lataire

【3】C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor
标题：C3 D-AD：通过可学习的顾问通过核心注意力实现连续3D异常检测
链接：https://arxiv.org/abs/2508.01311

作者：u, Hanzhe Liang, Jie Zhang, Chenxi Hu, Jinbao Wang, Can Gao
备注：We have provided the code for C3D-AD with checkpoints and BASELINE at this link: this https URL

【4】Maximize margins for robust splicing detection
标题：最大限度地提高裕度以实现稳健的拼接检测
链接：https://arxiv.org/abs/2508.00897

作者：mon de Kergunic (CRIStAL), Rony Abecidan (CRIStAL), Patrick Bas (CRIStAL), Vincent Itier (IMT Nord Europe, CRIStAL)
备注：in French language. GRETSI 2025 - Colloque Francophone de Traitement du Signal et des Images, this https URL, Aug 2025, Strasbourg, France

【5】Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models
标题：多变量时间序列基础模型中的幻觉检测和扩散缓解
链接：https://arxiv.org/abs/2508.00881

作者：hitwechkarn, Charles Fox, Ruchi Choudhary

【6】Reproducibility of Machine Learning-Based Fault Detection and Diagnosis for HVAC Systems in Buildings: An Empirical Study
标题：基于机器学习的建筑物空调系统故障检测和诊断的再现性：实证研究
链接：https://arxiv.org/abs/2508.00880

作者：tar, Michael Hadwiger, Franz Wotawa, Gerald Schweiger

【7】Detecting and measuring respiratory events in horses during exercise with a microphone: deep learning vs. standard signal processing
标题：使用麦克风检测和测量运动期间马的呼吸事件：深度学习与标准信号处理
链接：https://arxiv.org/abs/2508.02349

作者：M. Parmentier (1,2,3), Rhana M. Aarts (1), Elin Hernlund (4), Marie Rhodin (4), Berend Jan van der Zwaag (2,3) ((1) Utrecht University, (2) University of Twente, (3) Inertia Technology B.V., (4) Swedish University of Agricultural Sciences)

【8】Efficient optimization of expensive black-box simulators via marginal means, with application to neutrino detector design
标题：通过边际手段有效优化昂贵的黑匣子模拟器，并应用于中微子探测器设计
链接：https://arxiv.org/abs/2508.01834

作者：im, Simon Mak, Ann-Kathrin Schuetz, Alan Poon

分类|识别(5篇)

【1】Flexible Automatic Identification and Removal (FAIR)-Pruner: An Efficient Neural Network Pruning Method
标题：灵活的自动识别和删除（FAIR）-Pruner：一种有效的神经网络剪枝方法
链接：https://arxiv.org/abs/2508.02291

作者：Lin, Mostafa Hussien, Chengyao Yu, Mohamed Cheriet, Osama Abdelrahman, Ruixing Ming
备注：Submitted to AAAI 2026

【2】IMUCoCo: Enabling Flexible On-Body IMU Placement for Human Pose Estimation and Activity Recognition
标题：IMUCoCo：实现灵活的体内IMU放置，用于人体姿势估计和活动识别
链接：https://arxiv.org/abs/2508.01894

作者：ou, Riku Arakawa, Yuvraj Agarwal, Mayank Goel

【3】Hyperparameter-Free Neurochaos Learning Algorithm for Classification
标题：用于分类的无超参数神经混乱学习算法
链接：https://arxiv.org/abs/2508.01478

作者：nry, Nithin Nagaraj

【4】Hybrid Hypergraph Networks for Multimodal Sequence Data Classification
标题：用于多峰序列数据分类的混合超图网络
链接：https://arxiv.org/abs/2508.00926

作者：Hui Wang, Yuting Huang, Danwei Zhang, Zizhu Fan
备注：9 pages, 5 figures

【5】Inequalities for Optimization of Classification Algorithms: A Perspective Motivated by Diagnostic Testing
标题：分类算法优化的不等式：诊断测试驱动的视角
链接：https://arxiv.org/abs/2508.01065

作者：atrone, Anthony J. Kearsley

表征(4篇)

【1】Learning Unified System Representations for Microservice Tail Latency Prediction
标题：学习用于微服务尾部延迟预测的统一系统表示
链接：https://arxiv.org/abs/2508.01635

作者：ian, Hailiang Zhao, Tianlv Chen, Jiayi Chen, Ziqi Wang, Kingsum Chow, Shuiguang Deng

【2】A hierarchy tree data structure for behavior-based user segment representation
标题：用于基于行为的用户细分表示的分层树数据结构
链接：https://arxiv.org/abs/2508.01115

作者： Xuejiao Kang, Sathya Iyer, Idris Malik, Ruixuan Li, Juan Wang, Xinchen Lu, Xiangxue Zhao, Dayong Wang, Menghan Liu, Isaac Liu, Feng Liang, Yinzhe Yu
备注：18 pages, 7 figures

【3】v-PuNNs: van der Put Neural Networks for Transparent Ultrametric Representation Learning
标题：v-PuNN：用于透明超度量表示学习的van der Put神经网络
链接：https://arxiv.org/abs/2508.01010

作者：andry Regis N'guessan

【4】Learning Unified User Quantized Tokenizers for User Representation
标题：学习统一用户量化令牌器用于用户表示
链接：https://arxiv.org/abs/2508.00956

作者： Yang Chen, Wuliang Huang, Tianyi Zheng, Jianhu Chen, Bin Dou, Yice Luo, Yun Zhu, Baokun Wang, Yongchao Liu, Xing Fu, Yu Cheng, Chuntao Hong, Weiqiang Wang, Xin-Wei Yao

3D|3D重建等相关(3篇)

【1】SimDeep: Federated 3D Indoor Localization via Similarity-Aware Aggregation
标题：SimDeep：通过相似性感知聚合的联合3D室内定位
链接：https://arxiv.org/abs/2508.01515

作者：een, Sarah Elsamanody, Hamada Rizk, Moustafa Youssef
备注：Accepted for ICMU 2025 -- The 15th International Conference on Mobile Computing and Ubiquitous Networking, Busan, Korea, September 10--12, 2025. Nominated for Best Paper Award

【2】3DRot: 3D Rotation Augmentation for RGB-Based 3D Tasks
标题：3DRot：基于Ruby的3D任务的3D旋转增强
链接：https://arxiv.org/abs/2508.01423

作者：ang, Deyu Li, Xiaoke Jiang, Lei Zhang

【3】DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction
标题：DreamSat-2.0：走向通用单视图小行星3D重建
链接：https://arxiv.org/abs/2508.01079

作者：Diaz, Xinghui Hu, Josiane Uwumukiza, Giovanni Lavezzi, Victor Rodriguez-Fernandez, Richard Linares

编码器(1篇)

【1】WhiSQA: Non-Intrusive Speech Quality Prediction Using Whisper Encoder Features
标题：WhiSQA：使用Whisper编码器功能的非侵入性语音质量预测
链接：https://arxiv.org/abs/2508.02210

作者：ose, Kris Hong, Thomas Hain, Stefan Goetze
备注：Accepted at SPECOM 2025

优化|敛散性(15篇)

【1】Instance-Optimal Uniformity Testing and Tracking
标题：实例最佳均匀性测试和跟踪
链接：https://arxiv.org/abs/2508.02637

作者：, Clément L. Canonne, Erik Waingarten
备注：FOCS 2025, to appear

【2】BOOST: Bayesian Optimization with Optimal Kernel and Acquisition Function Selection Technique
标题：BOoster：具有最优核和采集函数选择技术的Bayesian优化
链接：https://arxiv.org/abs/2508.02332

作者： Park, Mujin Cheon, Dong-Yeun Koh
备注：12 pages

【3】Multi-Treatment-DML: Causal Estimation for Multi-Dimensional Continuous Treatments with Monotonicity Constraints in Personal Loan Risk Optimization
标题：多治疗-TLR：个人贷款风险优化中具有单调性约束的多维连续治疗的因果估计
链接：https://arxiv.org/abs/2508.02183

作者：o, Bo Wang, Cuiying Zhao, Tongyao Wan

【4】Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization
标题：用于自动广告竞价优化的生成性大规模预训练模型
链接：https://arxiv.org/abs/2508.02002

作者：iayang Zhao, Yilei Zhao, Zhaoqi Zhang, Linyou Cai, Qianlong Xie, Xingxing Wang

【5】Flow-Aware GNN for Transmission Network Reconfiguration via Substation Breaker Optimization
标题：基于流量感知GNN的变电站断路器优化输电网络重构
链接：https://arxiv.org/abs/2508.01951

作者：ng, Rabab Haider, Pascal van Hentenryck

【6】Optimizing Day-Ahead Energy Trading with Proximal Policy Optimization and Blockchain
标题：利用近距离政策优化和区块链优化未来能源交易
链接：https://arxiv.org/abs/2508.01888

作者：erma, Ying Xie

【7】Proactive Constrained Policy Optimization with Preemptive Penalty
标题：具有先发制人惩罚的主动约束政策优化
链接：https://arxiv.org/abs/2508.01883

作者：, Pengyu Wang, Guoqing Liu, Haifeng Zhang, Pin Lyu, Jun Wang

【8】VAGPO: Vision-augmented Asymmetric Group Preference Optimization for the Routing Problems
标题：VAGPO：路由问题的视觉增强不对称群体偏好优化
链接：https://arxiv.org/abs/2508.01774

作者：u, Bohan Tan, Yan Jin

【9】Neural Policy Iteration for Stochastic Optimal Control: A Physics-Informed Approach
标题：随机最优控制的神经政策迭代：一种基于物理学的方法
链接：https://arxiv.org/abs/2508.01718

作者： Kim, Yeoneung Kim, Minseok Kim, Namkyeong Cho

【10】A Reward-Directed Diffusion Framework for Generative Design Optimization
标题：生成式设计优化的奖励导向扩散框架
链接：https://arxiv.org/abs/2508.01509

作者：mati, Patrick Kirchen, Mohammed Hannan, Rajeev K. Jaiman

【11】Learning Pivoting Manipulation with Force and Vision Feedback Using Optimization-based Demonstrations
标题：使用基于优化的演示通过力和视觉反馈学习旋转操纵
链接：https://arxiv.org/abs/2508.01082

作者：ai, Kei Ota, Devesh K. Jha, Diego Romeres

【12】On Some Tunable Multi-fidelity Bayesian Optimization Frameworks
标题：关于一些可调多保真Bayesian优化框架
链接：https://arxiv.org/abs/2508.01013

作者：oj, Anastasia S. Georgiou, Dimitris G. Giovanis, Themistoklis P. Sapsis, Ioannis G. Kevrekidis

【13】Stochastic Optimal Control via Measure Relaxations
标题：通过测量松弛的随机最优控制
链接：https://arxiv.org/abs/2508.00886

作者：uehrle, Christoph Stiller
备注：7 pages, 4 figures

【14】Re-optimization of a deep neural network model for electron-carbon scattering using new experimental data
标题：使用新实验数据重新优化电子-碳散射深度神经网络模型
链接：https://arxiv.org/abs/2508.00996

作者：Kowal, Krzysztof M. Graczyk, Artur M. Ankowski, Rwik Dharmapal Banerjee, Jose L. Bonilla, Hemant Prasad, Jan T. Sobczyk
备注：14 pages, 12 figures

【15】Accelerating Fleet Upgrade Decisions with Machine-Learning Enhanced Optimization
标题：利用机器学习增强优化加速机队升级决策
链接：https://arxiv.org/abs/2508.00915

作者：owin Chai, Stefan Hildebrand, Tobias Lachnit, Martin Benfer, Gisela Lanza, Sandra Klinge

预测|估计(16篇)

【1】Pre-Tactical Flight-Delay and Turnaround Forecasting with Synthetic Aviation Data
标题：利用合成航空数据进行战术前飞行延误和周转预测
链接：https://arxiv.org/abs/2508.02294

作者：d Murad, Massimiliano Ruocco
备注：Preprint. Under review

【2】User Trajectory Prediction Unifying Global and Local Temporal Information
标题：统一全球和本地时间信息的用户轨迹预测
链接：https://arxiv.org/abs/2508.02161

作者：Bin Chong, Ronghua Ji, Chen Hou

【3】SpikeSTAG: Spatial-Temporal Forecasting via GNN-SNN Collaboration
标题：SpikeSTAG：通过GNN-SNN协作进行时空预测
链接：https://arxiv.org/abs/2508.02069

作者：Changze Lv, Mingjie Li, Yunpeng Liu, Xiaoqing Zheng, Fengzhe Zhang, Wei cao, Fan Zhang
备注：7 pages, 4 figures

【4】Epi$^2$-Net: Advancing Epidemic Dynamics Forecasting with Physics-Inspired Neural Networks
标题：Epi$#2 $-Net：利用物理启发的神经网络推进流行病动力学预测
链接：https://arxiv.org/abs/2508.02049

作者：Chenghua Gong, Tianjun Gu, Yuhao Zheng, Jie Ding, Juyuan Zhang, Liming Pan, Linyuan Lü

【5】Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting
标题：重振不规则多元时间序列预测的典型预调
链接：https://arxiv.org/abs/2508.01971

作者：, Yiming Huang, Yanyun Wang, Yuankai Wu, James Kwok, Yuxuan Liang
备注：Under review

【6】Improving Hospital Risk Prediction with Knowledge-Augmented Multimodal EHR Modeling
标题：利用知识增强的多模式EHR建模改进医院风险预测
链接：https://arxiv.org/abs/2508.01970

作者： Datta, Jiaming Cui, Zihan Guan, Rupesh Silwal, Joshua C Eby, Gregory Madden, Anil Vullikanti

【7】KANMixer: Can KAN Serve as a New Modeling Core for Long-term Time Series Forecasting?
标题：KANMixer：KAN能否成为长期时间序列预测的新建模核心？
链接：https://arxiv.org/abs/2508.01575

作者：ang, Yuping Wang, Yao Su, Shuo Xing, Wenjing Chen, Xin Zhang, Zhengzhong Tu, Ziming Zhang, Fangzhou Lin, Michael Zielewski, Kazunori D Yamada
备注：11 pages, 3 figures, 5 tables

【8】Frequency-Constrained Learning for Long-Term Forecasting
标题：用于长期预测的频率约束学习
链接：https://arxiv.org/abs/2508.01508

作者：ong, Vincent Zhihao Zheng, Lijun Sun

【9】UniExtreme: A Universal Foundation Model for Extreme Weather Forecasting
标题：UniExtreme：极端天气预报的通用基础模型
链接：https://arxiv.org/abs/2508.01426

作者：Weijia Zhang, Hao Liu
备注：35 pages, 80 figures, submitted to ACM KDD 2026 conference

【10】Cryptocurrency Price Forecasting Using Machine Learning: Building Intelligent Financial Prediction Models
标题：使用机器学习进行加密货币价格预测：构建智能财务预测模型
链接：https://arxiv.org/abs/2508.01419

作者：l Islam, Md Shafiqur Rahman, Md Sumsuzoha, Babul Sarker, Md Rafiqul Islam, Mahfuz Alam, Sanjib Kumar Shil

【11】Satellite Connectivity Prediction for Fast-Moving Platforms
标题：快速移动平台的卫星连通性预测
链接：https://arxiv.org/abs/2508.00877

作者： Babak Mafakheri

【12】A Data-Driven Machine Learning Approach for Predicting Axial Load Capacity in Steel Storage Rack Columns
标题：预测钢货架柱轴向承载力的数据驱动机器学习方法
链接：https://arxiv.org/abs/2508.00876

作者： Mammadli, Casim Yazici, Muhammed Gürbüz, İrfan Kocaman, F. Javier Dominguez-Gutierrez, Fatih Mehmet Özkal

【13】Visuo-Acoustic Hand Pose and Contact Estimation
标题：视觉声学手势和接触估计
链接：https://arxiv.org/abs/2508.00852

作者：, Uksang Yoo, Yunchao Yao, Shahram Najam Syed, Luca Bondi, Jonathan Francis, Jean Oh, Jeffrey Ichnowski

【14】Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes
标题：观察治疗中的对话：分类和预测行为代码
链接：https://arxiv.org/abs/1907.00326

作者：Michael Tanana, Zac E. Imel, Eric Poitras, David C. Atkins, Vivek Srikumar
备注：Accepted to ACL 2019

【15】FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms
标题：FastCSP：利用原子通用模型加速分子晶体结构预测
链接：https://arxiv.org/abs/2508.02641

作者：akhanyan, Yi Yang, Luis Barroso-Luque, Muhammed Shuaibi, Daniel S. Levine, Kyle Michel, Viachaslau Bernat, Misko Dzamba, Xiang Fu, Meng Gao, Xingyu Liu, Keian Noori, Lafe J. Purvis, Tingling Rao, Brandon M. Wood, Ammar Rizvi, Matt Uyttendaele, Andrew J. Ouderkirk, Chiara Daraio, C. Lawrence Zitnick, Arman Boromand, Noa Marom, Zachary W. Ulissi, Anuroop Sriram
备注：52 pages, 19 figures, 6 tables

【16】The Role of Review Process Failures in Affective State Estimation: An Empirical Investigation of DEAP Dataset
标题：回顾过程失败在情感状态估计中的作用--基于DEAP数据集的实证研究
链接：https://arxiv.org/abs/2508.02417

作者：Khan, Taylor Sweet, Chase A Harvey, Calder Knapp, Dean J. Krusienski, David E Thompson
备注：25 pages, 4 figures, This is a preprint version of the manuscript. It is intended for submission to a peer-reviewed journal

其他神经网络|深度学习|模型|建模(38篇)

【1】CAK: Emergent Audio Effects from Minimal Deep Learning
标题：CAK：来自最小深度学习的紧急音频效果
链接：https://arxiv.org/abs/2508.02643

作者：ckman
备注：8 pages, 3 figures, code and other resources at this https URL

【2】NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds
标题：NMC：通过多个集合体上的近内存采样进行高效边缘DNN训练
链接：https://arxiv.org/abs/2508.02313

作者：o, Haiduo Huang, Qiwei Dang, Wenzhe Zhao, Tian Xia, Pengju Ren

【3】CellForge: Agentic Design of Virtual Cell Models
标题：CellForge：虚拟细胞模型的简化设计
链接：https://arxiv.org/abs/2508.02276

作者：ang, Zhuoyun Yu, Jiapeng Chen, Yan Cui, Daniel Shao, Weixu Wang, Fang Wu, Yuchen Zhuang, Wenqi Shi, Zhi Huang, Arman Cohan, Xihong Lin, Fabian Theis, Smita Krishnaswamy, Mark Gerstein

【4】Skeleton-Guided Learning for Shortest Path Search
标题：最短路径搜索的神经网络引导学习
链接：https://arxiv.org/abs/2508.02270

作者：Liu, Xiao Li, Huan Li, Hua Lu, Christian S. Jensen, Jianliang Xu

【5】Pigeon-SL: Robust Split Learning Framework for Edge Intelligence under Malicious Clients
标题：Pigeon-SL：恶意客户端下边缘智能的稳健拆分学习框架
链接：https://arxiv.org/abs/2508.02235

作者：ark, Tony Q.S. Quek, Hyowoon Seo
备注：13 pages, 14 figures

【6】Fitness aligned structural modeling enables scalable virtual screening with AuroBind
标题：健康度一致的结构建模通过AuroBind实现可扩展的虚拟筛选
链接：https://arxiv.org/abs/2508.02137

作者：Zhang, Jiahua Rao, Jie Zhong, Weiqiang Bai, Dongxue Wang, Shaobo Ning, Lifeng Qiao, Sheng Xu, Runze Ma, Will Hua, Jack Xiaoyu Chen, Odin Zhang, Wei Lu, Hanyi Feng, He Yang, Xinchao Shi, Rui Li, Wanli Ouyang, Xinzhu Ma, Jiahao Wang, Jixian Zhang, Jia Duan, Siqi Sun, Jian Zhang, Shuangjia Zheng
备注：54 pages, 13 figures, code available at this https URL

【7】The Geometry of Machine Learning Models
标题：机器学习模型的几何结构
链接：https://arxiv.org/abs/2508.02080

作者：er, Jacques Ravel
备注：61 pages, 1 figure

【8】NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks
标题：NaviMaster：学习针对图形用户界面和预定导航任务的统一策略
链接：https://arxiv.org/abs/2508.02046

作者：o, Wentao Yan abd Jingyu Gong, Min Wang, Zhizhong Zhang, Xuhong Wang, Yuan Xie, Xin Tan
备注：Homepage: this https URL

【9】Diffusion models for inverse problems
标题：反问题的扩散模型
链接：https://arxiv.org/abs/2508.01975

作者：Chung, Jeongsol Kim, Jong Chul Ye

【10】RouteMark: A Fingerprint for Intellectual Property Attribution in Routing-based Model Merging
标题：RouteMark：基于竞争的模型合并中知识产权归属的指纹
链接：https://arxiv.org/abs/2508.01784

作者：unxi Shen, Zhenheng Tang, Xiaowen Chu, Bo Li, Ivor W. Tsang, Yew-Soon Ong
备注：MoE, Model Merging, Fingerprint

【11】CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications
标题：CultureGuard：面向多语言安全应用程序的文化感知数据集和Guard模型
链接：https://arxiv.org/abs/2508.01710

作者：oshi, Rakesh Paul, Kanishk Singla, Anusha Kamath, Michael Evans, Katherine Luna, Shaona Ghosh, Utkarsh Vaidya, Eileen Long, Sanjay Singh Chauhan, Niranjan Wartikar

【12】SPARTA: Advancing Sparse Attention in Spiking Neural Networks via Spike-Timing-Based Prioritization
标题：SPARTA：通过基于尖峰定时的优先级在尖峰神经网络中推进稀疏注意力
链接：https://arxiv.org/abs/2508.01646

作者：ng, Changick Kim
备注：9 pages, 4 figures, submitted to AAAI 2026

【13】Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learning
标题：用于异类多流学习的漂移感知协作协助专家混合
链接：https://arxiv.org/abs/2508.01598

作者：e Lu, Kun Wang, Xiaoyu Yang, Guangquan Zhang

【14】Diffusion Models for Future Networks and Communications: A Comprehensive Survey
标题：未来网络和通信的扩散模型：全面调查
链接：https://arxiv.org/abs/2508.01586

作者：ng Luong, Nguyen Duc Hai, Duc Van Le, Huy T. Nguyen, Thai-Hoc Vu, Thien Huynh-The, Ruichen Zhang, Nguyen Duc Duy Anh, Dusit Niyato, Marco Di Renzo, Dong In Kim, Quoc-Viet Pham
备注：This work was submitted to Proceedings of the IEEE

【15】Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs
标题：原型学习，从心电图中创建精细的可解释数字表型
链接：https://arxiv.org/abs/2508.01521

作者：hi, David Chen, Michael C. Burkhart, Nipun Bhandari, Bashar Ramadan, Brett Beaulieu-Jones
备注：Preprint; under review

【16】Canoe Paddling Quality Assessment Using Smart Devices: Preliminary Machine Learning Study
标题：使用智能设备评估独木舟桨板质量：初步机器学习研究
链接：https://arxiv.org/abs/2508.01511

作者： A. Lamelas, A. Hassan, P. Bhote
备注：30 pages, 16 figures, 4 tables

【17】ESM: A Framework for Building Effective Surrogate Models for Hardware-Aware Neural Architecture Search
标题：ESM：为硬件感知神经架构搜索构建有效代理模型的框架
链接：https://arxiv.org/abs/2508.01505

作者：ehman Nasir, Samroz Ahmad Shoaib, Muhammad Abdullah Hanif, Muhammad Shafique

【18】Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler
标题：热身-稳定-衰退学习率中冷却阶段的训练动态
链接：https://arxiv.org/abs/2508.01483

作者： Dremov, Alexander Hägele, Atli Kosson, Martin Jaggi
备注：Published in TMLR. Review: this https URL

【19】Fusion Sampling Validation in Data Partitioning for Machine Learning
标题：机器学习数据分区中的融合抽样验证
链接：https://arxiv.org/abs/2508.01325

作者：er Godwin Udomboso, Caston Sigauke, Ini Adinya
备注：23 pages, 10 figures

【20】Physics-Informed Neural Network Approaches for Sparse Data Flow Reconstruction of Unsteady Flow Around Complex Geometries
标题：物理信息神经网络方法用于复杂几何形状周围不稳定流的稀疏数据流重建
链接：https://arxiv.org/abs/2508.01314

作者： Krishna Malineni, Suresh Rajendran

【21】Foundation Models for Bioacoustics -- a Comparative Review
标题：生物声学基础模型--比较评论
链接：https://arxiv.org/abs/2508.01277

作者：chwinger, Paria Vali Zadeh, Lukas Rauch, Mats Kurz, Tom Hauschild, Sam Lapp, Sven Tomforde
备注：Preprint

【22】Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis
标题：本征神经网络：利用本征基础解锁可推广愿景
链接：https://arxiv.org/abs/2508.01219

作者：ng, Chenzhong Yin, Mingxi Cheng, Shukai Duan, Shahin Nazarian, Paul Bogdan

【23】T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
标题：T2 S：终身模仿学习的代币化技能扩展
链接：https://arxiv.org/abs/2508.01167

作者：Zhang, Jingyu Gong, Zhizhong Zhang, Xin Tan, Yanyun Qu, Yuan Xie

【24】Protecting Student Mental Health with a Context-Aware Machine Learning Framework for Stress Monitoring
标题：利用情境感知机器学习框架进行压力监测，保护学生心理健康
链接：https://arxiv.org/abs/2508.01105

作者：ul Islam Ovi, Jamal Hossain, Md Raihan Alam Rahi, Fatema Akter
备注：6 pages, 3 figures, 3 tables, 1 algorithm. Conference paper

【25】Flow Matching for Probabilistic Learning of Dynamical Systems from Missing or Noisy Data
标题：基于缺失或有噪数据的动态系统概率学习的流匹配
链接：https://arxiv.org/abs/2508.01101

作者： Rout, Eldad Haber, Stephane Gaudreault
备注：arXiv admin note: text overlap with arXiv:2503.12273

【26】The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's algorithm
标题：神经网络量化的格形几何--GPTQ和Babai算法的简短等效性证明
链接：https://arxiv.org/abs/2508.01077

作者：rnick
备注：9 pages, 4 figures

【27】ThermoCycleNet: Stereo-based Thermogram Labeling for Model Transition to Cycling
标题：TheroCyclleNet：基于立体感的热像图标签，用于模型过渡到骑自行车
链接：https://arxiv.org/abs/2508.00974

作者：drés López, Vincent Weber, Severin Zentgraf, Barlo Hillen, Perikles Simon, Elmar Schömer
备注：Presented at IWANN 2025 18th International Work-Conference on Artificial Neural Networks, A Coruña, Spain, 16-18 June, 2025. Book of abstracts: ISBN: 979-13-8752213-1. Funding: Johannes Gutenberg University "Stufe I'': "Start ThermoCycleNet''. Partial funding: Carl-Zeiss-Stiftung: "Multi-dimensionAI'' (CZS-Project number: P2022-08-010)

【28】Compression-Induced Communication-Efficient Large Model Training and Inferencing
标题：压缩诱导的沟通高效的大型模型训练和推理
链接：https://arxiv.org/abs/2508.00960

作者：Seal, Maksudul Alam, Jorge Ramirez, Sajal Dash, Hao Lu

【29】Enhancing material behavior discovery using embedding-oriented Physically-Guided Neural Networks with Internal Variables
标题：使用具有内部变量的面向嵌入的物理引导神经网络增强物质行为发现
链接：https://arxiv.org/abs/2508.00959

作者：oz-Sierra, Manuel Doblaré, Jacobo Ayensa-Jiménez

【30】Discrete approach to machine learning
标题：机器学习的离散方法
链接：https://arxiv.org/abs/2508.00869

作者：ashitsyn, Dmitriy Shabanov
备注：preprint, 52 pages, 37 figures

【31】Deploying Geospatial Foundation Models in the Real World: Lessons from WorldCereal
标题：在现实世界中部署地理空间基础模型：WorldCereal的教训
链接：https://arxiv.org/abs/2508.00858

作者： Butsko, Kristof Van Tricht, Gabriel Tseng, Giorgia Milli, David Rolnick, Ruben Cartuyvels, Inbal Becker Reshef, Zoltan Szantoi, Hannah Kerner

【32】Bike-Bench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints
标题：自行车长凳：具有目标和约束的生成模型的自行车设计基准
链接：https://arxiv.org/abs/2508.00830

作者：nwetter, Yazan Abu Obaideh, Fabien Chiotti, Ioanna Lykourentzou, Faez Ahmed

【33】Superior resilience to poisoning and amenability to unlearning in quantum machine learning
标题：量子机器学习中具有出色的中毒复原力和对取消学习的适应性
链接：https://arxiv.org/abs/2508.02422

作者：en, Shi-Xin Zhang
备注：9 pages, 4 figures with references and supplemental materials

【34】Comparing Generative Models with the New Physics Learning Machine
标题：生成模型与新物理学习机的比较
链接：https://arxiv.org/abs/2508.02275

作者：rossi, Marco Letizia, Riccardo Torre
备注：v1: 14 pages, 7 figures, 8 tables, additional material on GitHub referenced in the paper

【35】ByteGen: A Tokenizer-Free Generative Model for Orderbook Events in Byte Space
标题：ByteGen：字节空间中订单簿事件的无令牌化生成模型
链接：https://arxiv.org/abs/2508.02247

作者：Zhi Chen
备注：21 pages, 3 tables, 5 figures

【36】A Large-Scale Benchmark of Cross-Modal Learning for Histology and Gene Expression in Spatial Transcriptomics
标题：空间转录组学中组织学和基因表达跨模式学习的大规模基准
链接：https://arxiv.org/abs/2508.01490

作者： Gindra, Giovanni Palla, Mathias Nguyen, Sophia J. Wagner, Manuel Tran, Fabian J Theis, Dieter Saur, Lorin Crawford, Tingying Peng
备注：The code is accessible at: this https URL

【37】Inferring processes within dynamic forest models using hybrid modeling
标题：使用混合建模推断动态森林模型内的过程
链接：https://arxiv.org/abs/2508.01228

作者：n Pichler, Yannek Käber
备注：29 pages, 16 figures

【38】Uni-Mol3: A Multi-Molecular Foundation Model for Advancing Organic Reaction Modeling
标题：Uni-Mol 3：推进有机反应建模的多分子基础模型
链接：https://arxiv.org/abs/2508.00920

作者：, Junjie Wang, Zhifeng Gao, Xiaohong Ji, Rong Zhu, Xinyu Li, Linfeng Zhang, Guolin Ke, Weinan E

其他(54篇)

【1】Tensor Dynamic Mode Decomposition
标题：张量动态模式分解
链接：https://arxiv.org/abs/2508.02627

作者： Mengqi Hu, Yifei Lou, Can Chen
备注：6 pages, 4 figures, 1 table

【2】What are you sinking? A geometric approach on attention sink
标题：你在沉什么？注意力下沉的几何方法
链接：https://arxiv.org/abs/2508.02546

作者：uscio, Umberto Nanni, Fabrizio Silvestri

【3】Solved in Unit Domain: JacobiNet for Differentiable Coordinate Transformations
标题：在单位域中求解：JacobiNet用于可微坐标变换
链接：https://arxiv.org/abs/2508.02537

作者：Jianchuan Yang, Junjie Zhang, Runnan Yang, Xu Liu, Hong Wang, Ziyu Ren, Wenqi Hu
备注：Submitted to CMAME, revision in progress

【4】Causality and Interpretability for Electrical Distribution System faults
标题：配电系统故障的因果关系和解释性
链接：https://arxiv.org/abs/2508.02524

作者：eddi, Sai Ram Aditya Parisineni, Hemanth Macharla, Mayukha Pal

【5】On Distributional Dependent Performance of Classical and Neural Routing Solvers
标题：经典和神经路由求解器的分布相关性能
链接：https://arxiv.org/abs/2508.02510

作者：hyssens, Tim Dernedde, Wilson Sentanoe, Lars Schmidt-Thieme
备注：9 pages, 2 figures

【6】$ε$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
标题：$e $-Softmax：逼近单热载体以缓解标签噪音
链接：https://arxiv.org/abs/2508.02387

作者：Wang, Xiong Zhou, Deming Zhai, Junjun Jiang, Xiangyang Ji, Xianming Liu
备注：Accepted by NeurIPS2024

【7】A Novel Sliced Fused Gromov-Wasserstein Distance
标题：一种新颖的切片融合Groov-Wasserstein距离
链接：https://arxiv.org/abs/2508.02364

作者：ening, Robert Beinert

【8】Posterior Sampling of Probabilistic Word Embeddings
标题：概率词嵌入的后验抽样
链接：https://arxiv.org/abs/2508.02337

作者：änäinen, Isac Boström, Måns Magnusson, Johan Jonasson

【9】FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment
标题：FinWorld：一个用于端到端金融人工智能研究和部署的一体化开源平台
链接：https://arxiv.org/abs/2508.02292

作者：ang, Yilei Zhao, Chuqiao Zong, Xinrun Wang, Bo An

【10】mCardiacDx: Radar-Driven Contactless Monitoring and Diagnosis of Arrhythmia
标题：mCardiacDx：雷达驱动的非接触式心律失常监测和诊断
链接：https://arxiv.org/abs/2508.02274

作者：ar, Noppanat Wadlom, Jaeheon Kwak, Si-Hyuck Kang, Insik Shin
备注：15 pages, 27 images

【11】LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
标题：LeanK：可学习的K缓存通道修剪以实现高效解码
链接：https://arxiv.org/abs/2508.02215

作者：g, Zhiyuan He, Huiqiang Jiang, Chengruidong Zhang, Yuqing Yang, Jianyong Wang, Lili Qiu

【12】The Complexity of Extreme Climate Events on the New Zealand's Kiwifruit Industry
标题：极端气候事件对新西兰猕猴桃产业的复杂性
链接：https://arxiv.org/abs/2508.02130

作者：eng, Victor W. Chu, Zhidong Li, Evan Webster, Ashley Rootsey
备注：Pre-print v0.8 2025-08-04

【13】Trainable Dynamic Mask Sparse Attention
标题：可训练的动态面具稀疏注意力
链接：https://arxiv.org/abs/2508.02124

作者：i, Yifan Wu, Bingheng Wu, Yiran Peng, Liangdong Wang, Guang Liu, Yuyu Luo
备注：8 figures, 4 tables

【14】AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
标题：AlignGuard-LoRA：通过Fisher引导分解和Riemann-测地碰撞正规化进行保持对准的微调
链接：https://arxiv.org/abs/2508.02079

作者：as, Abhilekh Borah, Vinija Jain, Aman Chadha

【15】Confidence-Diversity Calibration of AI Judgement Enables Reliable Qualitative Coding
标题：人工智能判断的置信度多样性校准实现可靠的定性编码
链接：https://arxiv.org/abs/2508.02029

作者：hao, Yindi Liu
备注：23 pages, 5 figures. Code and data available at this https URL

【16】Kronecker-LoRA: hybrid Kronecker-LoRA adapters for scalable, sustainable fine-tuning
标题：Kronecker-LoRA：混合Kronecker-LoRA适配器，可扩展、可持续微调
链接：https://arxiv.org/abs/2508.01961

作者：n

【17】Stochastic Encodings for Active Feature Acquisition
标题：主动特征获取中的随机编码
链接：https://arxiv.org/abs/2508.01957

作者： Norcliffe, Changhee Lee, Fergus Imrie, Mihaela van der Schaar, Pietro Lio
备注：31 pages, 15 figures, 17 tables, published at ICML 2025

【18】Navigating High Dimensional Concept Space with Metalearning
标题：用元学习导航高维概念空间
链接：https://arxiv.org/abs/2508.01948

作者：

【19】Inferring Reward Machines and Transition Machines from Partially Observable Markov Decision Processes
标题：从部分可观测马尔可夫决策过程推断奖励机和转移机
链接：https://arxiv.org/abs/2508.01947

作者：Jiamou Liu, Libo Zhang
备注：12 pages, 7 figures. Under review as a conference paper. Source code is available at: this https URL

【20】IAUNet: Instance-Aware U-Net
标题：IAUNet：实例感知U-Net
链接：https://arxiv.org/abs/2508.01928

作者：Prytula, Illia Tsiporenko, Ali Zeynalli, Dmytro Fishman
备注：Published in CVPR Workshops (CVMI), 2025. Project page/code/models/dataset: $\href{https://slavkoprytula.github.io/IAUNet/}{\text{this https URL}}$

【21】EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses
标题：EgoTrigger：在全天节能智能眼镜中实现音频驱动图像捕获以增强人类记忆力
链接：https://arxiv.org/abs/2508.01915

作者：ruchuri, Sinan Hersek, Lavisha Aggarwal, Qiao Yang, Xin Liu, Achin Kulshrestha, Andrea Colaco, Henry Fuchs, Ishan Chatterjee
备注：15 pages, 6 figres, 6 tables. Accepted to ISMAR 2025 as a TVCG journal paper

【22】Causal Discovery in Multivariate Time Series through Mutual Information Featurization
标题：通过互信息特征化发现多元时间序列的因果关系
链接：https://arxiv.org/abs/2508.01848

作者：o Paldino, Gianluca Bontempi

【23】A Trainable Optimizer
标题：可训练的优化者
链接：https://arxiv.org/abs/2508.01764

作者：g, Diego Klabjan

【24】Generalized Kernelized Bandits: Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds
标题：广义核心化强盗：自我规范化的伯恩斯坦式无冲突不平等和遗憾界
链接：https://arxiv.org/abs/2508.01681

作者：aria Metelli, Simone Drago, Marco Mussi

【25】VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulation
标题：VFP：多模式机器人操纵的变分流量匹配策略
链接：https://arxiv.org/abs/2508.01622

作者：hai, Ce Hao

【26】IMU: Influence-guided Machine Unlearning
标题：IMU：影响引导的机器学习
链接：https://arxiv.org/abs/2508.01620

作者：, Jing Wu, Mingyi Zhou, Pengwei Liang, Dinh Phung

【27】Censored Sampling for Topology Design: Guiding Diffusion with Human Preferences
标题：Topology设计的审查抽样：以人类偏好引导传播
链接：https://arxiv.org/abs/2508.01589

作者：im, Keun Park, Yeoneung Kim

【28】The Vanishing Gradient Problem for Stiff Neural Differential Equations
标题：刚性神经方程的消失梯度问题
链接：https://arxiv.org/abs/2508.01519

作者：nk, Linda Petzold

【29】Instruction-based Time Series Editing
标题：基于指令的时间序列编辑
链接：https://arxiv.org/abs/2508.01504

作者：iu, Dongliang Guo, Brynne Sullivan, Teague R. Henry, Tom Hartvigsen

【30】Reconstructing Trust Embeddings from Siamese Trust Scores: A Direct-Sum Approach with Fixed-Point Semantics
标题：从Siamese信任分数重建信任嵌入：具有定点语义的直接和方法
链接：https://arxiv.org/abs/2508.01479

作者：ay, Taylan Alpay, Bugra Kilictas
备注：22 pages, 3 figures, 1 table

【31】Regression Augmentation With Data-Driven Segmentation
标题：使用数据驱动分割的回归增强
链接：https://arxiv.org/abs/2508.01455

作者：ahyari, Shiva Mehdipour Ghobadlou, Mike Domaratzki

【32】Effects of Feature Correlations on Associative Memory Capacity
标题：特征相关性对联想记忆容量的影响
链接：https://arxiv.org/abs/2508.01395

作者：elmeier, Gerald Friedland
备注：Accepted at ICLR 2025 "New Frontiers in Associative Memories" Workshop. Code: this https URL

【33】Quenched large deviations for Monte Carlo integration with Coulomb gases
标题：利用库伦气体消除蒙特卡罗积分的大偏差
链接：https://arxiv.org/abs/2508.01392

作者：enet, Mylène Maïda, Martin Rouault
备注：39 pages, 7 figures. Comments are welcome

【34】FedCD: A Fairness-aware Federated Cognitive Diagnosis Framework
标题：FedCD：一个具有公平意识的联邦认知诊断框架
链接：https://arxiv.org/abs/2508.01296

作者：g Yang, Jialin Han, Xiaoshan Yu, Ziwen Wang, Hao Jiang, Haiping Ma, Xingyi Zhang, Geyong Min
备注：25 pages, 5 figures

【35】Exploitation Is All You Need... for Exploration
标题：剥削就是你所需要的一切.勘探
链接：https://arxiv.org/abs/2508.01287

作者：tschler, Jesse Roberts

【36】RelMap: Reliable Spatiotemporal Sensor Data Visualization via Imputative Spatial Interpolation
标题：RelMap：基于虚拟空间插值的可靠时空传感器数据可视化
链接：https://arxiv.org/abs/2508.01240

作者：hen, Huayuan Ye, He Zhu, Siwei Fu, Changbo Wang, Chenhui Li
备注：9 pages, 14 figures, paper accepted to IEEE VIS 2025

【37】SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy
标题：SpectrumWorld：光谱学人工智能基金会
链接：https://arxiv.org/abs/2508.01188

作者：, Jiaqing Xie, Shuaike Shen, Daolang Wang, Yeyun Chen, Ben Gao, Shuzhou Sun, Biqing Qi, Dongzhan Zhou, Lei Bai, Linjiang Chen, Shufei Zhang, Jun Jiang, Tianfan Fu, Yuqiang Li

【38】From Taylor Series to Fourier Synthesis: The Periodic Linear Unit
标题：从泰勒数列到傅里叶合成：周期线性单位
链接：https://arxiv.org/abs/2508.01175

作者：o
备注：15 pages, 5 figures, for associated raw example files and the code repository, see this https URL

【39】Dataset Condensation with Color Compensation
标题：带颜色补偿的数据集浓缩
链接：https://arxiv.org/abs/2508.01139

作者：Duo Su, Junjie Hou, Guang Li

【40】The Promise of RL for Autoregressive Image Editing
标题：RL对自回归图像编辑的承诺
链接：https://arxiv.org/abs/2508.01119

作者：di, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad, Ge Ya Luo, Juan A. Rodriguez, Sai Rajeswar, Siva Reddy, Christopher Pal, Benno Krojer, Aishwarya Agrawal

【41】AutoSIGHT: Automatic Eye Tracking-based System for Immediate Grading of Human experTise
标题：AutoSIGHT：基于自动眼动追踪的系统，用于人类经验立即评分Tise
链接：https://arxiv.org/abs/2508.01015

作者：ling, Jozef Probcin, Adam Czajka
备注：This work has been accepted for publication in the proceedings of the IEEE VL/HCC conference 2025. The final published version will be available via IEEE Xplore

【42】FeatureCuts: Feature Selection for Large Data by Optimizing the Cutoff
标题：DeliverCuts：通过优化截止来选择大数据的特征
链接：https://arxiv.org/abs/2508.00954

作者：Devika Prasad, Luiz Pizzato, Nicholas Foord, Arman Abrahamyan, Anna Leontjeva, Cooper Doyle, Dan Jermyn
备注：11 pages, 4 figures, appendix

【43】SmartDate: AI-Driven Precision Sorting and Quality Control in Date Fruits
标题：SmartDate：人工智能驱动的枣类水果精准分拣和质量控制
链接：https://arxiv.org/abs/2508.00921

作者：kaf
备注：6 pages, 2 figures, published in Proceedings of the 21st IEEE International Conference on High Performance Computing and Networking (HONET 2024), Doha, Qatar, December 2024

【44】Cyber-Zero: Training Cybersecurity Agents without Runtime
标题：Cyber-Zero：在没有预设的情况下训练网络安全代理
链接：https://arxiv.org/abs/2508.00910

作者： Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, Zijian Wang
备注：Public Link: this https URL

【45】Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact
标题：GPT-2中的通用神经元：出现、持续性和功能影响
链接：https://arxiv.org/abs/2508.00903

作者：dan, Cheng-Ting Chou, Amrit Kurakula, Cole Blondin, Kevin Zhu, Vasu Sharma, Sean O'Brien

【46】ff4ERA: A new Fuzzy Framework for Ethical Risk Assessment in AI
标题：ff 4ERA：人工智能道德风险评估的新模糊框架
链接：https://arxiv.org/abs/2508.00899

作者：ub, Ivan Letteri, Francesca A. Lisi

【47】FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
标题：FECT：联系中心对话记录中人工智能生成的解释性声明的事实评估
链接：https://arxiv.org/abs/2508.00889

作者：Shin, Binoy Robin Dalal, Iwona Bialynicka-Birula, Navjot Matharu, Ryan Muir, Xingwei Yang, Samuel W. K. Wong
备注：Accepted for an oral presentation at Agentic & GenAI Evaluation KDD 2025: KDD workshop on Evaluation and Trustworthiness of Agentic and Generative AI Models

【48】FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
标题：FRAM：采用混合精度计算的Frobenius正规化指派匹配
链接：https://arxiv.org/abs/2508.00887

作者：en, Yuan Liang, Shengxin Zhu

【49】Learned LSM-trees: Two Approaches Using Learned Bloom Filters
标题：习得LSM树：使用习得布鲁姆过滤器的两种方法
链接：https://arxiv.org/abs/2508.00882

作者：Fidalgo, Puyuan Ye

【50】Cognitive Exoskeleton: Augmenting Human Cognition with an AI-Mediated Intelligent Visual Feedback
标题：认知外骨骼：利用人工智能介导的智能视觉反馈增强人类认知
链接：https://arxiv.org/abs/2508.00846

作者：u, Xinyu Zhang

【51】PCS Workflow for Veridical Data Science in the Age of AI
标题：人工智能时代真实数据科学的PCS工作流程
链接：https://arxiv.org/abs/2508.00835

作者：. Rewolinski, Bin Yu

【52】EngiBench: A Framework for Data-Driven Engineering Design Research
标题：EngiBench：数据驱动工程设计研究框架
链接：https://arxiv.org/abs/2508.00831

作者：elten, Gabriel Apaza, Gerhard Bräunlich, Cashen Diniz, Xuliang Dong, Arthur Drake, Milad Habibi, Nathaniel J. Hoffman, Matthew Keeler, Soheyl Massoudi, Francis G. VanGessel, Mark Fuge
备注：Under review

【53】ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation
标题：ACT-Tensor：财务数据集插补的张量完成框架
链接：https://arxiv.org/abs/2508.01861

作者： Jiayu Li, Duo Zhang, Elynn Chen

【54】Test-Time Training for Speech Enhancement
标题：语音增强的测试时间训练
链接：https://arxiv.org/abs/2508.01847

作者：Behera, Riya Ann Easow, Venkatesh Parvathala, K. Sri Rama Murty
备注：Accepted to Interspeech 2025. 5 pages, 2 figures

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