2026-09论文中文摘要
前沿大语言模型在符合指南且针对具体病例的肿瘤决策中的集体能力边界
A collective capability boundary in frontier large language models on guideline-conformant and case-specific oncology decision-making
arXiv 2608.28592 · 2026-09-01专家验证的STEM问答
Expert-validated STEM QA
arXiv 2608.28591 · 2026-09-01DS-Lighting：让智能体管控框架显式化以实现数据科学自动化
DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation
arXiv 2608.28590 · 2026-09-01非局域魔的精确量化
Exact quantification of nonlocal magic
arXiv 2608.28563 · 2026-09-01闭合模式是一种规范选择：认证代码世界模型中相对于可达性的拓扑结构
An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models
arXiv 2608.28541 · 2026-09-01混沌中的阶梯：测试时缩放何时、如何（或许还有为何）提升大语言模型的机器翻译性能
Ladders in Chaos: When, How, (and Perhaps Why) Does Test-Time Scaling Improve LLM Machine Translation
arXiv 2608.28496 · 2026-09-01Prove2Me：用于规模化数学形式化的开源协作平台
Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
arXiv 2608.28433 · 2026-09-01面向Web级电子商务的时序感知复购预测：用于多场景杂货推荐的生存模型
Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation
arXiv 2608.28393 · 2026-09-01GraspHOI：从单张野外图像重建带手指级抓取的全身3D人-物体交互
GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image
arXiv 2608.28386 · 2026-09-01推导OpenEuroLLM模型的缩放定律：学习率、批量大小与损失
Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss
arXiv 2608.28308 · 2026-09-01GeoFF3D：用于大规模无人机测绘的坐标锚定前馈重建方法
GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping
arXiv 2608.28288 · 2026-09-01中国日益缩小的本土偏见与不断提升的颠覆性影响：来自全球引用网络分析的证据
China's Shrinking Home Bias and Rising Disruptive Impact: Evidence from a Global Citation Network Analysis
arXiv 2608.28139 · 2026-09-01几何控制的动态张力测量法解析本征表面活性剂吸附动力学
Geometry-Controlled Dynamic Tensiometry Resolves Intrinsic Surfactant Adsorption Kinetics
arXiv 2608.28112 · 2026-09-01大型液体闪烁体探测器中大气中微子中性流相互作用产生的单信号事例的表征
Characterizing Single-Signal Events from Atmospheric-Neutrino Neutral-Current Interactions in Large Liquid Scintillator Detectors
arXiv 2608.28095 · 2026-09-01WeAgent-MMSearch：面向多模态搜索智能体的原生文本-视觉交互
WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents
arXiv 2608.28062 · 2026-09-01不破坏，而是验证：用于隐私保护大语言模型验证的对抗探针
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification
arXiv 2608.27954 · 2026-09-01可变形环的形状演化与动力学
Shape Evolution and Dynamics of Deformable Ring
arXiv 2608.27952 · 2026-09-01用于强化学习的从评分规则到代码的信用分配
Rubric-to-Code Credit Assignment for Reinforcement Learning
arXiv 2608.27906 · 2026-09-01类新星系统中热稳定吸积盘的动力学驱动坍缩
Dynamically driven collapse of a thermally stable accretion disk in a nova-like system
arXiv 2608.27878 · 2026-09-01铜上CO2加氢的模式特异性动力学：分子旋转的隐藏作用
Mode-Specific Dynamics of $\text{CO}_2$ Hydrogenation on Copper: The Hidden Role of Molecular Rotation
arXiv 2608.27850 · 2026-09-01OrbGNN：一种基于波函数的机器学习电子间表示方法
OrbGNN: A Wave function-based Machine Learning Interelectronic Representation
arXiv 2608.27806 · 2026-09-01用于频域模拟矢量矩阵乘法的频率同步电路模型
Frequency Synchronization Circuit Model for Analog Vector-Matrix Multiplication in the Frequency Domain
arXiv 2608.27765 · 2026-09-01LongGuard：针对安全护栏长上下文失效的机制分析与无训练缓解方案
LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails
arXiv 2608.27580 · 2026-09-01面向科学基础模型的大规模异构数据组织：以核聚变研究为例
Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study
arXiv 2608.27578 · 2026-09-01民主支配的机制：动态同意工程的系统动力学范式
The Mechanics of Democratic Dominance: A System Dynamics Paradigm for Dynamic Consent Engineering
arXiv 2608.27509 · 2026-09-01面向语言模型的准则引导强化学习综述
A Survey on Rubric-Guided Reinforcement Learning for Language Models
arXiv 2608.27505 · 2026-09-01XHotpotQA：多跳问答中跨语言知识组合的基准
XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering
arXiv 2608.27481 · 2026-09-01区分拓扑马约拉纳线与普通线段的量子电容特征
Distinguishing Quantum Capacitance Signatures of a Topological Majorana Wire from a Normal Wire Segment
arXiv 2608.27452 · 2026-09-01非消去交集猜想的反驳
Refutation of the Non-Cancelling Intersections Conjecture
arXiv 2608.27416 · 2026-09-01双标度平面$\boldsymbol{\{mathcal\textbf{N}\}} = 4$ SYM 与 Carroll 全息理论
Doubly-scaled planar $\mathcal{N} = 4$ SYM & Carroll Holography
arXiv 2608.27410 · 2026-09-01D2C-Routing：用于混合来源AI生成文本检测的维度到组成证据路由
D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection
arXiv 2608.27380 · 2026-09-01掩埋硅层捕获氧杂质实现Si/SiGe量子阱的迁移率提升
Mobility Enhancement in Si/SiGe Quantum Well Enabled by a Buried Si Layer Trapping Oxygen Impurities
arXiv 2608.27377 · 2026-09-01Fe-Se-H化合物的高温超导性
High-Temperature Superconductivity of the Fe-Se-H compound
arXiv 2608.27349 · 2026-09-01QuantumBoostNet：用于提升心脏超声视图识别准确率的经典-量子混合架构
QuantumBoostNet: Hybrid Classical-Quantum Cardiac View Identification
arXiv 2608.27302 · 2026-09-01用于累积量的多尺度圈顶点展开：$\phi^4_2$模型
Multiscale Loop Vertex Expansion for Cumulants, the $ϕ^4_2$ Model
arXiv 2608.27188 · 2026-09-01函数有向图的后继闭子集计数
Counting Successor-Closed Subsets of Functional Digraphs
arXiv 2608.27145 · 2026-09-01高电荷态钆的极紫外（EUV）外光谱
Beyond-EUV spectrum of highly-charged gadolinium
arXiv 2608.27097 · 2026-09-01大维度三次超曲面强逼近的算术纯性
Arithmetic purity of strong approximation for cubic hypersurfaces of large dimension
arXiv 2608.27027 · 2026-09-01用于智能边检系统中实时队列预测、管理与优化的多模态AI框架
A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems
arXiv 2608.27010 · 2026-09-01MVC-Bench：医学视觉-语言模型的校准基准测试
MVC-Bench: Benchmarking Calibration of Medical Vision-Language Models
arXiv 2608.27004 · 2026-09-01由殆周期作用产生的无约化交叉积 $C^*$-代数
Selfless Reduced Crossed Product $C^{*}$-Algebras Arising from Almost Periodic Actions
arXiv 2608.26987 · 2026-09-01Ga掺杂α-Al₂O₃的电子结构与带边特征：第一性原理研究
Electronic Structure and Band-Edge Character of Ga-Substituted $α$-Al$_2$O$_3$: A First-Principles Study
arXiv 2608.26977 · 2026-09-01仙女座XXV矮椭球星系的孤立星团
The solitary star cluster of the Andromeda XXV dwarf spheroidal
arXiv 2608.26959 · 2026-09-01RubricRM：基于动态评分规则的生成式奖励模型，用于图像生成与编辑
RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing
arXiv 2608.26956 · 2026-09-01高对比度谐振器系统中的波导：理论与快速计算
Waveguiding in systems of high contrast resonators: Theory and fast computations
arXiv 2608.26906 · 2026-09-01几何对热力学响应的影响
The Effect of Geometry on Thermodynamic Response
arXiv 2608.26898 · 2026-09-01Self-OPD：无需教师模型的流匹配模型的在线策略蒸馏
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher
arXiv 2608.26872 · 2026-09-01LiveSim：在多智能体直播生态系统中模拟环境塑造的用户
LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems
arXiv 2608.26849 · 2026-09-01网络心理测量学与大语言模型的结合：应用于信度审计的伊辛嵌入模型
Integrating Network Psychometrics and LLMs: The Ising-Embeddings-Model applied to Reliability Auditing
arXiv 2608.26790 · 2026-09-01有效场论修正光子传播下的Hayward黑洞引力透镜效应
Gravitational Lensing of Hayward Black Holes with EFT-Corrected Photon Propagation
arXiv 2608.26785 · 2026-09-01
