2026-09论文中文摘要
面向多语种口述历史研究的自动语音识别技术
Automatic Speech Recognition for Multilingual Oral History Research
arXiv 2609.04232 · 2026-09-07穿越地球的回飞镖：当自由下落不能最大化固有时间时
Boomeranging through the Earth: when free fall doesn't maximize proper time
arXiv 2609.04231 · 2026-09-07离散经典电磁学
Discrete classical electromagnetism
arXiv 2609.04230 · 2026-09-07在FLRW宇宙中通过新型CPL型$Om(z)$参数化探测暗能量动力学
Probing dark energy dynamics through a new CPL-type $Om(z)$ parametrization in FLRW Universe
arXiv 2609.04229 · 2026-09-07A-相对论：基于结构层的广义引力理论
A-Relativity: A General Theory of Gravity from Structure Sheaf
arXiv 2609.04228 · 2026-09-07量子数守恒：高能实验设计与分析中的一种工具
Quantum number conservation: a tool in the design and analysis of high energy experiments
arXiv 2609.04227 · 2026-09-07EffVOC：无需相位的基于频谱表示的低延迟高效语音波形重建方法
EffVOC: Low-Delay Efficient Speech Waveform Reconstruction from Spectral Representations Without Phase
arXiv 2609.04226 · 2026-09-07权衡存在于标签中：面向轮次感知的流式自动语音识别（ASR）的因果监督
The Trade-off Was in the Labels: Causal Supervision for Turn-Aware Streaming ASR
arXiv 2609.04225 · 2026-09-07超越SDR：音乐源分离如何重塑与节奏相关的信号特性
Beyond SDR: How Music Source Separation Reshapes Rhythm-Relevant Signal Properties
arXiv 2609.04224 · 2026-09-07语料选择对依存距离估计的影响有多大？
How Much Does Corpus Choice Change Dependency-Distance Estimates?
arXiv 2609.04223 · 2026-09-07GEPARD — 面向实时对话的生成式、韵律感知自回归文本转语音模型
GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue
arXiv 2609.04222 · 2026-09-07基于 scratchpad 的多核平台上分阶段执行实时任务的自动部署
Automated Deployment of Real-Time Tasks for Phased Execution on Scratchpad-Based Multicore Platforms
arXiv 2609.04221 · 2026-09-07代码大语言模型在受保护代码上的鲁棒性与权衡
Robustness and Trade-offs for Code LLMs on Protected Code
arXiv 2609.04220 · 2026-09-07用于微服务模糊测试的大语言模型：系统文献综述
Large Language Models for Fuzz Testing in Microservices: A Systematic Literature Review
arXiv 2609.04219 · 2026-09-07在相同推理成本下，多智能体结构无法胜过单个冻结智能体
At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent
arXiv 2609.04217 · 2026-09-07代码化工程：将软件工程方法论引入工程设计
Engineering as Code: Bringing Software Engineering Methodology to Engineering Design
arXiv 2609.04216 · 2026-09-07日志气味检测的系统文献综述
A systematic literature review on logging smell detection
arXiv 2609.04215 · 2026-09-07软件工程工作流程中LLM辅助的混合方法实证研究
A Mixed-Method Empirical Study of LLM Assistance in Software Engineering Workflows
arXiv 2609.04214 · 2026-09-07面向模型驱动的数字孪生配置：通过SysML、SAREF和Ditto分离结构语义与运行时
Toward Model-Driven Digital Twin Configuration: Separating Structure Semantics and Runtime with SysML SAREF and Ditto
arXiv 2609.04213 · 2026-09-07软件架构的重大问题：ICSE 2026 软件架构 BoF 报告
Big Questions on Software Architecture: Report of the ICSE 2026 BoF on Software Architecture
arXiv 2609.04212 · 2026-09-07流程挖掘中事件日志生成的数据相关挑战与需求：系统文献综述
Data-Related Challenges and Requirements for Event Log Generation in Process Mining: A Systematic Literature Review
arXiv 2609.04211 · 2026-09-07SH-PDOPS：AI驱动的云原生企业可靠性框架，用于预测分析与智能DevOps自动化
SH-PDOPS: AI-Driven Cloud Native Enterprise Reliability Framework for Predictive Analytics and Intelligent DevOps Automation
arXiv 2609.04210 · 2026-09-07提示三角：关于提示作为混合制品的注册报告
The Prompt Triangle: A Registered Report on Prompts as Hybrid Artifacts
arXiv 2609.04209 · 2026-09-07AI生成代码，人类承担债务：智能体生成代码的可持续性与演化实证研究
AI Writes Code, Humans Pay the Debt. An Empirical Study on the Sustainability and Evolution of Agent-Generated Code
arXiv 2609.04208 · 2026-09-07打破字母排序：重新思考代码评审中的文件排序
Breaking the Alphabet: Rethinking File Ordering in Code Review
arXiv 2609.04207 · 2026-09-07语音AI客户服务中的偏见与安全性审计
Auditing Bias and Safety in Voice AI Customer Care
arXiv 2609.04206 · 2026-09-07DTM：基于树型相似度的黑盒测试套件最小化的确定性方法
DTM: Deterministic Approaches for Black-box Test Suite Minimization with Tree-based Similarity
arXiv 2609.04205 · 2026-09-07具身多媒体：教程
Embodied Multimedia: A Tutorial
arXiv 2609.04204 · 2026-09-07顺序式优于联合式：论在线蒸馏与可验证奖励强化学习的相互作用
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
arXiv 2609.04108 · 2026-09-07硬件预取的置信门控准入：当门比预测器更重要时
Confidence-Gated Admission for Hardware Prefetching: When the Gate Matters More Than the Predictor
arXiv 2609.04040 · 2026-09-07可编辑视觉设计
Editable Visual Design
arXiv 2609.04034 · 2026-09-07梯度下降（非）任意时刻加速的更强下界
Stronger Lower Bounds for (Non-)Anytime Acceleration of Gradient Descent
arXiv 2609.04032 · 2026-09-07针对重尾分布的极值分位数处理效应的位置不变估计量
A Location-Invariant Estimator of Extremal Quantile Treatment Effects for Heavy-Tailed Distributions
arXiv 2609.04018 · 2026-09-07LLM4CKD：用于早期慢性肾病筛查的大型语言模型
LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening
arXiv 2609.04013 · 2026-09-07三角形网格最长边二分法的闭包复杂度
Closure complexity of longest-edge bisection for triangular meshes
arXiv 2609.04003 · 2026-09-07接口诱导的轨迹审查
Interface-Induced Trajectory Censoring
arXiv 2609.03966 · 2026-09-07固定后缀依赖率：量化拉脱维亚语借词中性属指派的双轨机制
Fixed Suffix Dependency Ratio: Quantifying the Dual-Track Mechanism of Gender Assignment in Latvian Loanwords
arXiv 2609.03930 · 2026-09-07各向极小曲面与周长极小化子的半空间定理
A Halfspace Theorem for Global Anisotropic Perimeter Minimizers
arXiv 2609.03916 · 2026-09-07FWBC-VLA：面向接触丰富型移动操纵的力感知全身补偿
FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation
arXiv 2609.03889 · 2026-09-07Xiaomi-TabLDM：表格基础模型技术报告
Xiaomi-TabLDM: A Tabular Foundation Model Technical Report
arXiv 2609.03880 · 2026-09-07VisCAD：具备多模态工业计算机辅助设计智能的基础模型套件
VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence
arXiv 2609.03811 · 2026-09-07IndicSafeEval：多语言劝诱式越狱攻击下大语言模型的安全鲁棒性
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks
arXiv 2609.03781 · 2026-09-07RealCADBench：面向工业设计意图的参数化CAD建模基准
RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents
arXiv 2609.03773 · 2026-09-07AlcaTRAz——针对越狱攻击的锚定树规则防御
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
arXiv 2609.03693 · 2026-09-07基于ℓ₁正则化电阻的生成树计数改进算法
An $m+n^{3/2}$ algorithm for counting spanning trees by $\ell_1$-regularized resistance
arXiv 2609.03574 · 2026-09-07蕴含Z^d上伯努利键渗流的θ(p_c)=0的一个猜想
A finite-graph conjecture related to $θ(p_c)=0$ for Bernoulli bond percolation on $\mathbb Z^d$
arXiv 2609.03492 · 2026-09-07UniCon：一种以统一上下文为中心的CTR预测建模范式
UniCon: A Unified Context-Centric Modeling Paradigm for CTR Prediction
arXiv 2609.03290 · 2026-09-07傅里叶曲线星座的符号域合并：逐轮比特缩减的精确代价
Symbol-Domain Chase Combining on Fourier-Curve Constellations: Exact Penalties of Per-Round Bit Reduction
arXiv 2609.03262 · 2026-09-07FOXDEN：面向AI就绪型科学数据集的FAIR服务
FOXDEN: FAIR Services for AI-Ready Scientific Datasets
arXiv 2609.03105 · 2026-09-07对称与伪对称数值半群的间隙多项式临界点的幂和
Power sums of critical points of gap polynomials for symmetric and pseudo-symmetric numerical semigroups
arXiv 2609.03049 · 2026-09-07
