2026-09论文中文摘要
可证明完备的基于LLM的广义规划
Provably Complete Generalized Planning with LLMs
arXiv 2609.27105 · 2026-09-24当直接操作变成猜测：AI介导的多感官可视化中的生产性摩擦
When Direct Manipulation Becomes a Guess: Productive Friction in AI-Mediated Multisensory Visualization
arXiv 2609.27104 · 2026-09-24薛定谔桥的量子增强采样
Quantum-Enhanced Sampling of Schrödinger Bridges
arXiv 2609.27103 · 2026-09-24铁磁/压电双层结构中磁子泵浦引起的共振增强声子输运
Resonantly Enhanced Phonon Transport by Magnon Pumping in a Ferromagnetic/Piezoelectric Bilayer
arXiv 2609.27101 · 2026-09-24密码学安全并不足够：Renegade 去中心化暗池中的隐私漏洞
Cryptographic Security Is Not Enough: Privacy Gaps in the Renegade Decentralized Dark Pool
arXiv 2609.27100 · 2026-09-24用于微创神经外科的单端口三臂机器人工具的设计与建模
Design and Modeling of a Single-Port Three-Arm Robotic Tool for Minimally Invasive Neurosurgery
arXiv 2609.27099 · 2026-09-24异常软光子产生可理解为强子化过程中的光子发射
Anomalous soft photon production can be understood as photon emission during hadronisation
arXiv 2609.27098 · 2026-09-24跨具身智能
Intelligence Across Embodiments
arXiv 2609.27095 · 2026-09-24姿态感知的希腊传统音乐多模态自动标注
Pose-Aware Multimodal Automatic Tagging for Greek Traditional Music
arXiv 2609.27094 · 2026-09-24阿拉斯加上空的局地12小时波：利用钠激光雷达的经向风测量
The Localized 12-hour Wave Over Alaska: Leveraging Meridional Wind Measurements From the Sodium Lidar
arXiv 2609.27093 · 2026-09-24已训练图神经网络中的局部证据与几何读出修复
Local Evidence and Geometric Readout Repair in Trained GNNs
arXiv 2609.27092 · 2026-09-24Solidity 遇上 LLM：一种基于 Transformer 的智能合约漏洞检测方法
Solidity Meets LLMs: A Transformer-Based Approach to Smart Contract Vulnerability Detection
arXiv 2609.27091 · 2026-09-24划分与怀疑：面向检索增强生成的多样化分布式投毒
Divide and Doubt: Diverse Distributed Poisoning for Retrieval-Augmented Generation
arXiv 2609.27090 · 2026-09-24挠 $F$-规范丛的 Harder-Narasimhan 滤过
Harder-Narasimhan filtration of torsion F-gauges
arXiv 2609.27089 · 2026-09-24蜈蚣水面游泳及其机器人物理模型
Water Surface Swimming in a Centipede and its Robophysical Model
arXiv 2609.27088 · 2026-09-24政策即技能：具有证据、确定性控制和审计的受治理LLM决策支持
Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit
arXiv 2609.27087 · 2026-09-24NADI 2026：第二届多方言阿拉伯语语音处理共享任务
NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task
arXiv 2609.27086 · 2026-09-24Crossflow：面向智能体LLM服务的预填充-解码弹性机制
Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving
arXiv 2609.27085 · 2026-09-24伽罗瓦轨道结构、拉马努金和与分圆余弦公式的稳定范围坍缩
Galois-Orbit Structure, Ramanujan Sums, and Stable-Range Collapse for Cyclotomic Cosine Formulas
arXiv 2609.27084 · 2026-09-24面向5G空中无线网络的AI无线传播建模与无线电环境地图
AI-Enabled Wireless Propagation Modeling and Radio Environment Maps for 5G Aerial Wireless Networks
arXiv 2609.27083 · 2026-09-24面向光谱类测量的软传感器开发的自动化特征区域选择
Automated feature-region selection for soft-sensor development from spectral-like measurements
arXiv 2609.27082 · 2026-09-24CECILIA：宇宙正午低电离气体过量星云发射的多线约束
CECILIA: Multi-line Constraints on Excess Nebular Emission from Low-Ionization Gas at Cosmic Noon
arXiv 2609.27081 · 2026-09-24mKdV呼吸子的鲁棒性：数值视角
Robustness of mKdV Breathers: A Numerical Perspective
arXiv 2609.27080 · 2026-09-24光谱学特征揭示体态磁性拓扑绝缘体中的持久激子凝聚
Spectroscopic signatures of persistent exciton condensation in a bulk magnetic topological insulator
arXiv 2609.27079 · 2026-09-24模型不确定性下运动预测的快速方向条件可达性
Fast Direction-Conditioned Reachability for Motion Prediction Under Model Uncertainty
arXiv 2609.27077 · 2026-09-24Pro-Bench：面向真实异构环境的提示鲁棒开放词汇视觉定位基准
Pro-Bench: Prompt-Robust Open-Vocabulary Visual Grounding Across Real-World Heterogeneous Environments
arXiv 2609.27076 · 2026-09-24构建跨世界中介效应估计量的单世界混合形式
Formulating Cross-World Mediation Estimands Through Single-World Mixtures
arXiv 2609.27075 · 2026-09-24量化神秘：使用机器学习方法对印度教与佛教神祇的比较研究
Quantifying the Occult: A Comparative Study of Hindu and Buddhist Deities Using Machine Learning Methods
arXiv 2609.27074 · 2026-09-24通过暗区化学平衡实现逆相变
Inverse phase transitions via dark sector chemical equilibration
arXiv 2609.27073 · 2026-09-24可编程相干记忆核用于波导量子电动力学中的量子储层计算
Programmable Coherent Memory Kernels for Quantum Reservoir Computing in Waveguide QED
arXiv 2609.27072 · 2026-09-24紧致双曲曲面中闭测地线的尖锐有效等分布
Sharp effective equidistribution of closed geodesics in compact hyperbolic surfaces
arXiv 2609.27071 · 2026-09-24高斯分布就够了：微调大型行为模型时流匹配先验并无帮助
The Gaussian Is Enough: Flow-Matching Priors Do Not Help When Fine-Tuning Large Behavior Models
arXiv 2609.27070 · 2026-09-24图结构在微服务根因分析中是否名副其实？RCAEval 上的受控研究，以及基准真正衡量的是什么
Does Graph Structure Earn Its Place in Microservice Root-Cause Analysis? A Controlled Study on RCAEval, and What the Benchmark Was Really Measuring
arXiv 2609.27069 · 2026-09-24HiRE：用于策略微调的事后奖励编辑
HiRE: Hindsight Reward Editing for Policy Finetuning
arXiv 2609.27068 · 2026-09-24ChipMEM：面向EDA智能体的验证接地记忆
ChipMEM: Verification-Grounded Memory for EDA Agents
arXiv 2609.27067 · 2026-09-24评估随着逆变器资源渗透率上升的电网强度
Evaluating Grid Strength with Rising Penetration of Inverter Based Resources
arXiv 2609.27066 · 2026-09-24混沌安德烈夫弹球中的热力学不确定性关系
Thermodynamic Uncertainty Relations in Chaotic Andreev Billiards
arXiv 2609.27065 · 2026-09-24当事实验证分数提升时会发生什么变化？训练验证器与LLM的证据及答案核算
What Changes When Fact-Verification Scores Improve? Evidence and Answer Accounting Across Trained Verifiers and LLMs
arXiv 2609.27064 · 2026-09-24学生使用LLM与数据科学课程中AI生成题目难度的局限性
Student Use of LLMs and the Limits of AI-Generated Question Difficulty in Data Science Courses
arXiv 2609.27063 · 2026-09-24Kolmogorov流中精确稳态的目录
A catalog of exact steady states in Kolmogorov flow
arXiv 2609.27062 · 2026-09-24$L^2(T)$ 上的伴随、序与谱模
Adjoints, Order and Spectral Moduli on $L^2(T)$
arXiv 2609.27061 · 2026-09-24类型 $B$ 和 $D$ 中反射因子分解的 Hurwitz 等价性
Hurwitz Equivalence of Reflection Factorizations in Types $B$ and $D$
arXiv 2609.27060 · 2026-09-24伊利诺伊社会态度聚合语料库（ISAAC）：一种用于大规模分析社会群体话语的开放工具与可复现流程
The Illinois Social Attitudes Aggregate Corpus (ISAAC): An Open Tool and Reproducible Pipeline for Analyzing Social Group Discourse at Scale
arXiv 2609.27059 · 2026-09-24阶段监督的潜在推理用于单次JavaScript反混淆
Stage-Supervised Latent Reasoning for Single-Shot JavaScript Deobfuscation
arXiv 2609.27058 · 2026-09-24盘截断触发高吸积率超大质量黑洞的相对论性喷流发射
Disk truncation triggers relativistic jet launching of a highly accreting supermassive black hole
arXiv 2609.27057 · 2026-09-24指向范畴的保守函子
Conservative functors to pointed categories
arXiv 2609.27056 · 2026-09-24一种简易小型化恒星干涉仪：用掩膜望远镜测量金星的角直径
A Simple Miniaturized Stellar Interferometer: Measuring the Angular Diameter of Venus with a Masked Telescope
arXiv 2609.27055 · 2026-09-24无势垒的量子限制
On quantum confinement without barriers
arXiv 2609.27054 · 2026-09-24非通用变分量子电路的最大可达性与一般可达性的等价性
Equivalence of maximal and generic reachability for non-universal Variational Quantum Circuits
arXiv 2609.27053 · 2026-09-24基于轻量级入侵检测的KubeEdge架构服务可用性改进
Improving Service Availability in KubeEdge-Based Architectures Using Lightweight Intrusion Detection
arXiv 2609.27052 · 2026-09-24
