2026-08论文中文摘要
检索关系，检测谬误：一种用于政治辩论分析的RAG方法
Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate Analysis
arXiv 2608.27471 · 2026-08-31选择，而非训练：基于大语言模型（LLM）选择的模块化实体消歧的优势
Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection
arXiv 2608.27470 · 2026-08-31用物理信息神经网络重构广义巴罗全息暗能量
Reconstructing the generalized Barrow holographic dark energy with physics-informed neural networks
arXiv 2608.27469 · 2026-08-31SN 2023ixf中心引擎的多信使约束：中子星还是黑洞？
Multimessenger Constraints on the Central Engine in SN 2023ixf: Neutron Star or Black Hole?
arXiv 2608.27468 · 2026-08-31UIC-AIHealth4All参加ArchEHR-QA 2026：面向临床问答的优先答案式证据定位
UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering
arXiv 2608.27467 · 2026-08-31PACE：基于智能体自动化的发布者自适应内容提取
PACE: Publisher-Adaptive Content Extraction via Agentic Automation
arXiv 2608.27466 · 2026-08-31情绪语境对大语言模型支持仓促决策的影响：六种商业模型的情绪脆弱性比较
The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models
arXiv 2608.27465 · 2026-08-31并非所有解释都被寻求：面向以人为中心的可解释人工智能的信息寻求心理学
Not All Explanations Are Sought: Information-Seeking Psychology for Human-Centered XAI
arXiv 2608.27464 · 2026-08-31大锤还是手术刀？用于隐性仇恨言论检测的细粒度自适应框架
Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech
arXiv 2608.27462 · 2026-08-31SciReC：基于自适应交互的多模态多轮关系推理诊断评估
SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction
arXiv 2608.27461 · 2026-08-31基于向量索引的输出嵌入加速大语言模型推理
Accelerating LLM Inference via Vector Index Based Output Embeddings
arXiv 2608.27460 · 2026-08-31可测试人类知识的时间胶囊：单个免费本地模型中的41年《危险边缘！》
Time Capsule of Testable Human Knowledge: 41 Years of Jeopardy! in a Single Free Local Model
arXiv 2608.27459 · 2026-08-31基于图结构电子占据的离散流匹配的机理反应预测
Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
arXiv 2608.27429 · 2026-08-31理解用于大语言模型推理的进化策略：比GRPO更广泛的推理覆盖范围
Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO
arXiv 2608.27351 · 2026-08-31索伯列夫极值处线性化p-拉普拉斯算子的完整谱
The complete spectrum of the linearized $p$-Laplacian at a Sobolev extremal
arXiv 2608.27276 · 2026-08-31基于利润的冬小麦施氮量推荐机器学习评估
Accurate prediction is not profitable advice: profit-based evaluation of machine learning nitrogen recommendations in winter wheat
arXiv 2608.27205 · 2026-08-31多类动力学交通流模型：离散速度公式与扩散修正的宏观极限
A multi-class kinetic traffic flow model: discrete-velocity formulation and diffusively-corrected macroscopic limits
arXiv 2608.27159 · 2026-08-31布尔反链的计数
Counting Boolean Antichains
arXiv 2608.27126 · 2026-08-31GRAFT：面向精细机器人操作的 grounded 高效在线强化适应
GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation
arXiv 2608.27079 · 2026-08-31SpatialCrafter：基于生成式3D代理的单图像世界建模
SpatialCrafter: Single Image World Modeling with Generative 3D Proxies
arXiv 2608.27073 · 2026-08-31基于22nm工艺技术的TiN动力学电感谐振器实现的快速片上温度测量
Fast On-Chip Thermometry with TiN Kinetic Inductance Resonators in 22 nm Process Technology
arXiv 2608.27057 · 2026-08-31不同粒度层级下的韩语成分结构表示与分析
Representing and Parsing Korean Constituency Structure at Different Levels of Granularity
arXiv 2608.27035 · 2026-08-31用于基于偏微分方程（PDE）的贝叶斯反问题的量子辅助框架
A quantum-assisted framework for PDE-based Bayesian inverse problems
arXiv 2608.27028 · 2026-08-31环面向量丛与垂直方程组的零点数量
Toric vector bundles and the number of zeros of vertical systems
arXiv 2608.27019 · 2026-08-31ProRetrieval：通过可执行程序合成学习编排混合搜索
ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis
arXiv 2608.27017 · 2026-08-31TempJail：针对图像到视频生成模型的时序越狱攻击
TempJail: Temporal Jailbreak Attacks against Image-to-Video Generation Models
arXiv 2608.26971 · 2026-08-31autowerkstatt4null：面向汽车维修厂的车外诊断生态系统
autowerkstatt4null: An Off-Board-Diagnostics Ecosystem for Car-Workshops
arXiv 2608.26911 · 2026-08-31气候物理动态匹配
Climate Physics Dynamic Matching
arXiv 2608.26907 · 2026-08-31顺序很重要：面向视觉-语言推理的中文多面板梗图基准
Order Matters: A Chinese Multi-Panel Meme Benchmark for Vision-Language Reasoning
arXiv 2608.26866 · 2026-08-31AgentFold：用于蛋白质折叠模型设计的闭环智能体搜索
AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design
arXiv 2608.26747 · 2026-08-31用于知识图谱数值属性预测的带嵌入的神经回归
Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs
arXiv 2608.26729 · 2026-08-31LiveVVT：高保真实时视频虚拟试穿
LiveVVT: High-Fidelity Video Virtual Try-On in Real Time
arXiv 2608.26714 · 2026-08-31用于HSX仿星器原位磁场监测的AlGaN/GaN霍尔效应传感器
AlGaN/GaN Hall-Effect Sensor for In-Situ Magnetic Field Monitoring of the HSX Stellarator
arXiv 2608.26704 · 2026-08-31谱Barron空间中的热方程
Heat equations in spectral Barron spaces
arXiv 2608.26657 · 2026-08-31用于低温电子学的测温量子布朗模型
A thermometric quantum Brownian model for low-temperature electronics
arXiv 2608.26646 · 2026-08-31启动受限且可替代：为何三种推理优化在混合专家（MoE）模型中无法取得成效
Launch-Bound and Substitutable: Why Three Inference Optimizations Fail to Pay Off in Mixture-of-Experts Models
arXiv 2608.26612 · 2026-08-31通过用大规模辅助样本扩充极小目标样本实现效率提升
On efficiency gains via augmenting a tiny sample with a massive auxiliary sample
arXiv 2608.26610 · 2026-08-31面向临床诊断的大语言模型训练中知识图谱的外科式对齐
Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models
arXiv 2608.26587 · 2026-08-31MnF₂中弱交替磁交换的场放大读出
Field-amplified readouts of weak altermagnetic exchange in MnF$_2$
arXiv 2608.26540 · 2026-08-31次扩散逆问题的后验一致性
Posterior Consistency for Recovering Initial States in Nonlinear Subdiffusion Equations
arXiv 2608.26536 · 2026-08-312026年科学计算下一代生态系统研讨会报告：利用社区、软件与AI推进跨学科团队科学
Report of the 2026 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science
arXiv 2608.26519 · 2026-08-31作为博弈的微观结构演化
Microstructure evolution as a game
arXiv 2608.26484 · 2026-08-31Redwood：一款由AI从头设计、验证并在2周内部署的前沿AI加速器
Redwood: A Frontier AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AI
arXiv 2608.26418 · 2026-08-31MegaWave射电探测器
The MegaWave Radio Surveyor
arXiv 2608.26322 · 2026-08-31飞行聚焦脉冲中非线性正负电子对产生的增强
Enhancement of nonlinear pair production in a flying-focus pulse
arXiv 2608.26313 · 2026-08-31推进多层超结构研究——复杂光学元件的简单设计
Moving forward with multilayer metastructures - simple design of complex optics
arXiv 2608.26298 · 2026-08-31作为局域相位的统计：伊丁规范理论中涌现二聚体的晶体序与淬火动力学
Statistics as a local phase: crystalline order and quench dynamics of emergent dimers in Ising gauge theories
arXiv 2608.26264 · 2026-08-31土耳其检索增强生成（RAG）系统的分块与嵌入策略比较
Comparing Chunking and Embedding Strategies for Turkish RAG Systems
arXiv 2608.26192 · 2026-08-31自生成文本识别：LLM评估中的质量启发式、跨任务迁移与下游偏差
Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation
arXiv 2608.26159 · 2026-08-31人工智能模型可预测并协同调节人类的记忆搜索
AI Models Can Predict and Collaboratively Modulate Human Memory Search
arXiv 2608.26152 · 2026-08-31
