2026-08论文中文摘要
PARAssist：面向模糊用户请求的个性化自适应机器人辅助框架
PARAssist: A Framework for Personalized and Adaptive Robotic Assistance from Ambiguous User Requests
arXiv 2608.24905 · 2026-08-27面向单惯性测量单元（IMU）活动识别的动态影响加权蒸馏
Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition
arXiv 2608.24904 · 2026-08-27基于证据的多模态人体感知心理跨诊断维度映射
Evidence-Grounded Mapping of Multimodal Human Sensing Psychological Transdiagnostic Dimensions
arXiv 2608.24903 · 2026-08-27超越聊天机器人：通过双角色生成式AI助手实现共学与共教
Beyond the Chatbot: Co-Learning and Co-Teaching through a Dual-Persona Generative-AI Assistant
arXiv 2608.24902 · 2026-08-27检测≠可靠控制：可解码的共情方向在自动共情评分中仅产生最多部分偏移
Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores
arXiv 2608.24901 · 2026-08-27与散文写作相比，代码写作期间大脑活动与大语言模型（LLM）嵌入之间的对齐性更强
Stronger Alignment between Brain Activity and LLM Embeddings during Code Writing compared to Prose Writing
arXiv 2608.24900 · 2026-08-27aipsy-judge：一种针对对话式AI心理安全性的、经心理学家校正的专用本地评判器
aipsy-judge: A Specialized, Psychologist-Corrected Local Judge for the Psychological Safety of Conversational AI
arXiv 2608.24899 · 2026-08-27基于MCP的AI驱动屏幕阅读器智能体的可访问性树标准化
MCP-Driven Accessibility Tree Standardization for AI-Powered Screen Reader Agents
arXiv 2608.24898 · 2026-08-27保守乘性级联的精确拓扑：一种超度量转移算子亏格
Exact topology of conservative multiplicative cascades: An ultrametric transfer-operator genus
arXiv 2608.24897 · 2026-08-27智能体世界分析（AWA）——一种探索系统与支持决策的替代方法
Agentic World Analysis (AWA) - an alternative way to explore systems and support decision making
arXiv 2608.24896 · 2026-08-27用于评估时间编码中神经变异性的实时闭环协议
Real-time closed-loop protocol to assess neural variability in temporal coding
arXiv 2608.24895 · 2026-08-27自然语言输入、语义航迹表示与大语言模型推理：使海上信息交换模型可处理
Natural Language Input, Semantic Track Representation, and LLM Inference: Making the Maritime Information Exchange Model Tractable
arXiv 2608.24892 · 2026-08-27具有有限采样泛化保证的量子学习中的测量预算分配
Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees
arXiv 2608.24891 · 2026-08-27非洲的人工智能驱动心理健康聊天机器人：系统综述与文化适应框架
AI-Powered Mental Health Chatbots in Africa: A Systematic Review and Culturally Adaptive Framework
arXiv 2608.24890 · 2026-08-27面向大规模供应链运营的可靠大语言模型驱动决策引擎：架构、安全性与性能保证
Reliable LLM-Powered Decision Engines for Large-Scale Supply Chain Operations: Architecture, Safety, and Performance Guarantees
arXiv 2608.24889 · 2026-08-27面向肿瘤学领域数字患者导航工具的用户中心设计：范围综述
User-Centered Design for Digital Patient-Navigation Tools in Oncology: Scoping Review
arXiv 2608.24887 · 2026-08-27基于视觉语言模型的建筑布局多粒度图自动表示方法，用于设计信息学
VLM-based automatic multi-granularity graph representation of building layouts for design informatics
arXiv 2608.24886 · 2026-08-27Graphix：基于测量的量子计算软件框架
Graphix: A software framework for Measurement-Based Quantum Computation
arXiv 2608.24781 · 2026-08-27隐形编辑层：形式化部署语言模型中未公开的推理时调控、概率置放与归因问题
The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models
arXiv 2608.24662 · 2026-08-27Simthesizer：面向LLM服务系统的智能体驱动仿真框架
Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems
arXiv 2608.24650 · 2026-08-27低空间与通信复杂度的异步可验证信息分散
Asynchronous Verifiable Information Dispersal with Low Space and Communication Complexity
arXiv 2608.24636 · 2026-08-27IAPO：面向多轮服务智能体信用分配的感知影响策略优化
IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents
arXiv 2608.24588 · 2026-08-27通过逐次揭示实现撕纸信道容量
Achieving Torn-Paper Channel Capacity with Successive Revelation
arXiv 2608.24506 · 2026-08-27用于MKID读出的高隔离度宽带信道化器：基于RFSoC的自定义HLS实现
A high-isolation wideband channelizer for MKID readouts: a custom HLS implementation on RFSoC
arXiv 2608.24459 · 2026-08-27用于持续知识图谱嵌入中候选集干扰的匹配超额排序器正则化
Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding
arXiv 2608.24273 · 2026-08-27Opals.jl：Julia语言中用于数据同化的全面可组合框架
Opal.jl: a comprehensive, composable framework for data assimilation in Julia
arXiv 2608.24265 · 2026-08-27适用于Q2NS/ns-3中量子中继器链的Dynamic-Kernel/QPacket可执行程序
A Dynamic-Kernel/QPacket Executable for Quantum Repeater Chains in Q2NS/ns-3
arXiv 2608.24152 · 2026-08-27面向机器人操作的轨迹级连续动作表示
Trajectory-Level Continuous Action Representation for Robotic Manipulation
arXiv 2608.24111 · 2026-08-27AgentWorld：面向智能体信息检索的人格感知可靠性评估
AgentWorld: Personality-Aware Reliability Evaluation for Agentic Information Retrieval
arXiv 2608.24076 · 2026-08-27用于间歇性和孤立拓扑转变的尖锐-扩散界面模型
A sharp-diffuse interface model for intermittent and isolated topological transitions
arXiv 2608.24030 · 2026-08-27通过推理实现多样性：利用大语言模型群体的智慧进行未来预测
Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Prediction
arXiv 2608.24001 · 2026-08-27AI找到了一种方法
AI Finds A Way
arXiv 2608.23875 · 2026-08-27BotScan：一种用于大规模识别活跃物联网僵尸网络C2服务器的自适应主动探测方法
BotScan: An adaptive active probing approach for identifying live IoT Botnet C2 servers at scale
arXiv 2608.23854 · 2026-08-27等待时学习行动：考虑推理延迟的通用机器人策略的强化学习微调
Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency
arXiv 2608.23831 · 2026-08-27巡航控制与自适应巡航控制的统一动力学建模框架
A unified dynamical modeling framework for cruise control and adaptive cruise control
arXiv 2608.23827 · 2026-08-27股票策略回测：运气还是优势？MinervaScore作为统计稳健性评级
Equity Strategy Backtesting: Luck or Edge? The MinervaScore as a Statistical Robustness Grade
arXiv 2608.23808 · 2026-08-27紧致黎曼流形上生成式扩散模型的物种形成理论
A Theory of Speciation in Generative Diffusion Models on Compact Riemannian Manifolds
arXiv 2608.23798 · 2026-08-27通过图神经网络味识别探索ESSνSB近水切伦科夫探测器设计
Exploring ESS$ν$SB Near Water Cherenkov Detector Designs Through Graph Neural Network Flavour Identification
arXiv 2608.23773 · 2026-08-27利用下一代引力波探测器定义双黑洞并合的高阶记忆信号并预测其观测前景
Defining higher memory signals and forecasting their observation prospects for binary-black-hole mergers with next-generation gravitational-wave detectors
arXiv 2608.23739 · 2026-08-27利用伊奥夫时间分布对质子进行飞秒级成像
Femtoscale imaging of the proton with Ioffe-time distributions
arXiv 2608.23737 · 2026-08-27世界模型的柏拉图式表征假说
Platonic Representation Hypothesis on World Models
arXiv 2608.23720 · 2026-08-27基于模拟的宽线区半径-光度关系质量控制框架
A simulation-based quality-control framework for the broad-line region radius-luminosity relation
arXiv 2608.23673 · 2026-08-27自信地出错，悄无声息：对已部署的端侧语言模型不可检测故障的审计
Confidently Wrong, Silently So: Auditing Undetectable Failures of a Deployed On-Device Language Model
arXiv 2608.23663 · 2026-08-27PACT：面向FPGA时序收敛的后路由代理检查点调优
PACT: Post-route Agentic Checkpoint Tuning for FPGA Timing Closure
arXiv 2608.23602 · 2026-08-27物理空间的曲率与几何投影：量子力学与相对论的一种可能几何理解
Curvature of Physical Space and Geometric Projection: A Possible Geometric Understanding of Quantum Mechanics and Relativity
arXiv 2608.23581 · 2026-08-27基于主张提取与对齐的跨语言传记丰富
Cross-lingual Biography Enrichment via Claim Extraction and Alignment
arXiv 2608.23390 · 2026-08-27FASHI DR2：132个低红移氢原子21厘米吸收系统星表
FASHI DR2: A Catalog of 132 Low-Redshift HI 21 cm Absorption Systems
arXiv 2608.23385 · 2026-08-27超越点预测：面向公共政策的不确定性感知卫星贫困制图
Beyond Point Predictions: Uncertainty-Aware Satellite Poverty Mapping for Public Policy
arXiv 2608.23322 · 2026-08-27函数域上拟射影簇的等分布
Equidistribution for quasi-projective varieties over function fields
arXiv 2608.23239 · 2026-08-27动态逆：一种用于飞行控制设计的增量式演进方法
Dynamic Inversion: An Incrementally Evolving Methodology for Flight Control Design
arXiv 2608.23229 · 2026-08-27
