2026-08论文中文摘要
Poly-InstructTTS：基于开放式指令学习野外场景下的高表现力语音合成
Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions
arXiv 2608.20387 · 2026-08-24非互易热传递推进柔性热电器件发展
Non-reciprocal heat transfer advances flexible thermoelectric devices
arXiv 2608.20386 · 2026-08-24利用人类与大语言模型（LLM）的分歧改进基于核查表的质量评估
Using Human-LLM Disagreement to Improve Checklist-Based Quality Appraisal
arXiv 2608.20385 · 2026-08-24基于线性判别树集成的可解释多模态分类
Interpretable Multimodal Classification with Linear Discriminant Tree Ensembles
arXiv 2608.20384 · 2026-08-24机械滥用下锂离子电池热失控的红外热点引导预警
Infrared Hotspot-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Under Mechanical Abuse
arXiv 2608.20383 · 2026-08-24用于多模态理解与生成的解耦式视觉-语言系统
Decoupled Vision-Language System for Multimodal Understanding and Generation
arXiv 2608.20382 · 2026-08-24EditPPT：基于结构化工具使用多智能体与双模态验证器的忠实长文档幻灯片编辑
EditPPT: Faithful Long-Deck Slide Editing via Structured Tool-Using Multi-Agent with Dual-Modal Validators
arXiv 2608.20381 · 2026-08-24基于fMRI的疾病诊断的可解释性信息分解脑图学习
Interpretable Information-Decomposed Brain Graph Learning for fMRI-based Disease Diagnosis
arXiv 2608.20380 · 2026-08-24多模态智能体框架的基础与前沿：技术及应用综述
A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications
arXiv 2608.20379 · 2026-08-24真相藏于深处：通过潜在意图验证对抗语义伪装
Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification
arXiv 2608.20378 · 2026-08-24TH-GNN：用于检测大语言模型智能体刷单攻击的异质性时序图神经网络
TH-GNN: Heterogeneous Temporal Graph Neural Networks for LLM-Agent Shilling Attack Detection
arXiv 2608.20376 · 2026-08-24GRAFT：基于自适应DLM的草稿树构建与目标蒸馏边评分
GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring
arXiv 2608.20375 · 2026-08-24面向美国联邦公路管理局（FHWA）桥梁检查合规性的基于边缘的智能体检索增强生成
Edge-Based Agentic Retrieval-Augmented Generation for Autonomous FHWA Bridge Inspection Compliance
arXiv 2608.20372 · 2026-08-24当大语言模型（LLM）取代微调的自然语言理解（NLU）模型？面向生产型对话系统意图检测的决策框架
When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
arXiv 2608.20371 · 2026-08-24使用XPerf对智能体AI工作负载的大语言模型服务系统进行基准测试
Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf
arXiv 2608.20370 · 2026-08-24ASTAR：从大规模临床自由文本语料库自动生成标准化放射学报告模板
ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora
arXiv 2608.20369 · 2026-08-24基于文本特征分析的研究论文质量识别
Research Paper Quality Recognition Through Textual Feature Analysis
arXiv 2608.20368 · 2026-08-24面向家禽生产中福利约束控制的混合边缘-云数字孪生
A Hybrid Edge Cloud Digital Twin for Welfare-Constrained Control in Poultry Production
arXiv 2608.20367 · 2026-08-24用于蛋白质-配体柔性对接的调和扭转扩散
Harmonic Torsional Diffusion for Protein-Ligand Flexible Docking
arXiv 2608.20366 · 2026-08-24大型语言模型时代的圣训计算科学：批判性叙事综述
Hadith computational science in the age of large language models: a critical narrative review
arXiv 2608.20364 · 2026-08-24RLVR中的多语言验证器偏差：基准、推理诊断与跨语言选择瓶颈
Multilingual Verifier Bias in RLVR: Benchmark, Rollout Diagnosis, and the Cross-Lingual Selection Bottleneck
arXiv 2608.20362 · 2026-08-24迈向自动研究：利用具有分类结构的论文知识图谱挖掘可证伪的研究思路
Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure
arXiv 2608.20361 · 2026-08-24TriPLU：在小型语言模型中通过直接三线性乘积前馈网络绕过门控机制
TriPLU: Bypassing the Gate with Direct Trilinear Product FFNs in Tiny Language Models
arXiv 2608.20360 · 2026-08-24用于更快推理模型的自推测技术
Self-Speculation for Faster Reasoning Models
arXiv 2608.20359 · 2026-08-24bikiDATA：用于查询和探索大规模RDF数据集的Python库
bikiDATA: A Python Library to Query and Explore Large-Scale RDF Datasets
arXiv 2608.20358 · 2026-08-24先澄清再搜索：面向端到端 nugget 恢复的深度搜索澄清基准
Clarify-Then-Search: A Clarification Benchmark for Deep Search with End-to-End Nugget Restoration
arXiv 2608.20357 · 2026-08-24解耦结构与语义：模式表示如何影响基于大语言模型（LLM）的SQL生成
Disentangling Structure and Semantics: How Schema Representation Affects LLM-Based SQL Generation
arXiv 2608.20356 · 2026-08-24ExpertIVS：大型语言模型中由社会学专家驱动的个体价值观模拟
ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models
arXiv 2608.20355 · 2026-08-24NeuroStrata：用于精神压力动态脑网络分析的脑电连接感知深度表示学习框架
NeuroStrata: An Electroencephalographic Connectivity-Aware Deep Representation Learning Framework for Dynamic Brain Network Analysis of Mental Stress
arXiv 2608.20354 · 2026-08-24分歧假说：揭示心理健康自然语言处理中的词汇干扰与标签偏差
The Divergence Hypothesis: Unmasking Lexical Interference and Label Bias in Mental Health NLP
arXiv 2608.20353 · 2026-08-24幽灵回声：检索支持型应用中的语义擦除失效
Ghost Echoes: Semantic Erasure Failure in Retrieval-Backed Applications
arXiv 2608.20352 · 2026-08-24针对合成英语RAG探针中文化标记谓词触发的PII放大的分析性无检测探索：谓词资源混淆审计
Exploratory As-Analyzed No-Detection of Culturally-Marked Predicate-Triggered PII Amplification in a Synthetic-English RAG Probe: A Predicate-Resource-Confounded Audit
arXiv 2608.20351 · 2026-08-24如何训练一个实用的硅基智能管家？将复杂业务工作流内化至单个模型
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
arXiv 2608.20350 · 2026-08-24提示工程之外：提示词词汇敏感性及其对质量影响的系统性分析
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
arXiv 2608.20349 · 2026-08-24用于临床长上下文推理的抑制注意力：电子病历处理中中间信息丢失效应的表征与缓解
Inhibitory Attention for Clinical Long-Context Reasoning: Characterizing and Mitigating Lost-in-the-Middle Effects in EHR Processing
arXiv 2608.20348 · 2026-08-24语言模型认为谁具备胜任能力？职业偏见的机制分析
Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias
arXiv 2608.20347 · 2026-08-24构建并评估面向电信客服场景的合成孟加拉语语音资源
Building and Evaluating a Synthetic Bengali Speech Resource for Telecom Customer Care
arXiv 2608.20346 · 2026-08-24当词汇理解失效于临床推理：评估面向阿尔法世代（Gen Alpha，2010-2024年出生）的治疗机器人的安全风险
When Vocabulary Comprehension Fails Clinical Reasoning: Evaluating Therapy Bots' Safety Risks for Generation Alpha
arXiv 2608.20345 · 2026-08-24超越原始文本记录：面向基于大语言模型的数字孪生的结构化角色提取
Beyond Raw Transcripts: Structured Persona Extraction for LLM-Based Digital Twins
arXiv 2608.20344 · 2026-08-24结合可解释人工智能（XAI）分析的混合重采样与堆叠集成技术的破产预测
Bankruptcy Prediction via Hybrid Resampling and Stacking Ensemble Techniques with Explainable Artificial Intelligence (XAI)-Driven Analysis
arXiv 2608.20343 · 2026-08-24PrimeAgentOrchestrator：用于个人AI基础设施的内存初始化智能体生成器
PrimeAgentOrchestrator: Memory-Primed Agent Spawning for Personal AI Infrastructure
arXiv 2608.20342 · 2026-08-24SDAD：面向AI原生软件开发生命周期的规范驱动智能体开发
SDAD: Spec-Driven Agentic Development for the AI-Native SDLC
arXiv 2608.20341 · 2026-08-24Swift-Image：探索紧凑统一图像生成模型的性能前沿
Exploring the Performance Frontier of Compact Unified Image Generation Models
arXiv 2608.20334 · 2026-08-24学习何时思考：面向测试时计算分配的自适应推理
Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation
arXiv 2608.20256 · 2026-08-24直接与间接数据驱动控制：切换系统稳定性的案例研究
Direct vs. Indirect Data-Driven Control: Case-study of Switching Systems Stability
arXiv 2608.20207 · 2026-08-24关于8维空间中4-形式的注记
A note on 4-forms in 8-dimensions
arXiv 2608.20200 · 2026-08-24确定一维时空下某些非线性偏微分方程基本解的嵌套导数准则
The nested derivative criterion for determining elementary solutions to certain non-linear PDEs in one-dimensional space-time
arXiv 2608.20150 · 2026-08-24利用近似误差的强化学习用于长时间量子模拟
Reinforcement Learning to Harness Approximation Errors for Long-Time Quantum Simulation
arXiv 2608.20139 · 2026-08-24SAKE：用于几何刘维尔传输的谱自动微分核展开——量子动力学系统中响应传输的微分几何框架
SAKE: Spectral Autodiff Kernel Expansion for Geometric Liouvillian Transport. A Differential-Geometric Framework for Response Transport in Quantum Dynamical Systems
arXiv 2608.20132 · 2026-08-24DECOWAM：用于腿式移动操作的解耦全身世界-动作模型
DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation
arXiv 2608.20114 · 2026-08-24
