2026-09论文中文摘要
HF-SID：面向基于位置服务中生成式检索的高保真语义ID
HF-SID: High-Fidelity Semantic IDs for Generative Retrieval in Location-Based Services
arXiv 2608.30479 · 2026-09-01大型智能体：面向持久智能体的感知中心架构
Agents in the Large: Perception-Centered Architecture for Persistent Agents
arXiv 2608.30478 · 2026-09-01SNAD：大数据时代的发现赋能
SNAD: enabling discovery in the era of big data
arXiv 2608.30477 · 2026-09-01ImageEval 2026：基于文化语境的阿拉伯语多模态评估
ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation
arXiv 2608.30475 · 2026-09-01有界差分隐私下包含信念的后验-先验比率的界
Bounds on the Posterior-to-Prior Ratios for Inclusion Belief under Bounded Differential Privacy
arXiv 2608.30473 · 2026-09-01ToxLens：一种可复现的图学习框架，用于感知数据泄露、不确定性校准的分子毒性预测
ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction
arXiv 2608.30472 · 2026-09-01用于视觉地形导航的HorizonNet
HorizonNet for visual terrain navigation
arXiv 2608.30471 · 2026-09-01用于Signorini问题的障碍正则化对称Nitsche方法
A Barrier-Regularized Symmetric Nitsche Method for the Signorini Problem
arXiv 2608.30470 · 2026-09-01揭示水合盐脱水机制的多尺度研究
A multi-scale study to unravel the dehydration mechanism of hydrated salts
arXiv 2608.30469 · 2026-09-01Hi-Q：用于多跳问答的分层证据引导查询细化方法
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
arXiv 2608.30468 · 2026-09-01超越准确率：域偏移下解剖学引导的胸部X射线分类中肺部归因的量化
Beyond Accuracy: Quantifying Pulmonary Attribution in Anatomy-Guided Chest X-Ray Classification Under Domain Shift
arXiv 2608.30467 · 2026-09-01CHASE：当排序成为唯一目标时，内容生态系统如何被重塑
CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target
arXiv 2608.30466 · 2026-09-01增强用于可互操作联邦SPARQL评估的LargeRDFBench
Strengthening LargeRDFBench for Interoperable Federated SPARQL Evaluation
arXiv 2608.30465 · 2026-09-01纳米限域下不饱和钙溶液中的粘弹性界面结构
Viscoelastic interfacial structures in undersaturated calcium solutions under nanoconfinement
arXiv 2608.30464 · 2026-09-01能力更强，忠实度更低：大语言模型中数学（不）可解性检测的多语言分析
More Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMs
arXiv 2608.30463 · 2026-09-01通过高资源语言特征迁移提升低资源语言推理能力
Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer
arXiv 2608.30462 · 2026-09-01从最终产物到轨迹：面向证据支撑的长文本生成的回溯过程监督
From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation
arXiv 2608.30461 · 2026-09-01利用明亮孪生光束的鬼红外光谱
Ghost infrared spectroscopy with bright twin beams
arXiv 2608.30460 · 2026-09-01小红点及类似致密核的宽带宿主测量需要源相关多色点扩散函数（PSF）
Broad-band host measurements of little red dots and similar compact nuclei require source-conditioned polychromatic PSFs
arXiv 2608.30459 · 2026-09-01基于混合CNN-Transformer架构的联邦多任务学习用于膀胱肿瘤分割与MIBC分类
Federated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture
arXiv 2608.30458 · 2026-09-01学习结果变化的位置：面向多模态几何的信用可寻址推理
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry
arXiv 2608.30457 · 2026-09-01用于婴儿哭声分析的自监督预文本任务：受控比较及Donateacry上的警示性结果
Self-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry
arXiv 2608.30456 · 2026-09-01工作在强耦合区的超导微波谐振器耦合两个独立的磁振子谐振器
Coupling of two individual magnon resonators via a superconducting microwave resonator operating in the strong coupling regime
arXiv 2608.30454 · 2026-09-01多读取编辑信道上用于短块长度、高码率编码的标记分隔码
Marker-Delimited Codes for Short-Blocklength, High-Rate Coding over Multi-Read Edit Channels
arXiv 2608.30453 · 2026-09-01受控管流中的减阻与亚临界湍流
Drag reduction and subcritical turbulence in controlled pipe flows
arXiv 2608.30452 · 2026-09-01SeqAlign3DVG：用于3D视觉定位的序列对齐基准与体素推理框架
SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding
arXiv 2608.30451 · 2026-09-01FlowVVTON：基于流引导的无掩码视频虚拟试穿
FlowVVTON: Flow-Guided Mask-Free Video Virtual Try-On
arXiv 2608.30450 · 2026-09-01PRIME：通过插件式残差输入条件混合专家缓解共享CTR顶层网络中的子组优化竞争
PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert
arXiv 2608.30449 · 2026-09-01高维Kerr-NUT-(A)dS空间中黎曼张量的结构
Structure of the Riemann tensor in higher-dimensional Kerr-NUT-(A)dS spaces
arXiv 2608.30448 · 2026-09-01平面边界存在时的Gribov副本以及杨-米尔斯理论中的涌现边界规范不变性
Examples of Gribov copies in the presence of planar boundaries, and an emergent boundary gauge invariance in Yang-Mills theory
arXiv 2608.30447 · 2026-09-01面向包含小盘股的投资组合的不定成对相关矩阵端到端神经收缩
End-to-End Neural Shrinkage of Indefinite Pairwise Correlation Matrices for Small-Cap-Inclusive Portfolios
arXiv 2608.30446 · 2026-09-01磁弹性框架下线性弹性椭圆薄膜壳理论的推导
Derivation of a linearly elastic elliptic membrane shell theory in the framework of magnetoelasticity
arXiv 2608.30445 · 2026-09-01面向低功耗脉冲神经网络的非均匀内存分区
Non-uniform Memory Partitioning For Low-Power Spiking Neural Networks
arXiv 2608.30444 · 2026-09-01带物理真空的可压缩欧拉方程的光滑自相似解
On smooth self similar solution to compressible Euler equation with physical vacuum
arXiv 2608.30443 · 2026-09-01伪装成改进的混杂因素：针对129000例患者登记研究中卒中抗血栓治疗的离线强化学习的系统评估
Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry
arXiv 2608.30442 · 2026-09-01ECLIPSE：针对长视程智能体系统的自演化隐蔽提示注入攻击
ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems
arXiv 2608.30441 · 2026-09-01曲面稳定余切丛上丰富的仿射代数结构
Abundance of affine algebraic structures on stabilized cotangent bundles of surfaces
arXiv 2608.30440 · 2026-09-01面向神经形态硬件的、具有稀疏神经活动的事件驱动语言模型
Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware
arXiv 2608.30439 · 2026-09-01弹道石墨烯约瑟夫森结中的倏逝模卡西米尔-约瑟夫森力与栅控共振
Evanescent-mode Casimir-Josephson force and gate-controlled resonances in ballistic graphene Josephson junctions
arXiv 2608.30438 · 2026-09-01I型双希格斯二重态模型中CP-偶希格斯玻色子衰变到Vγ的双圈QCD修正
Two-loop QCD corrections to $CP$-even Higgs boson decays into $Vγ$ in the Type-I Two-Higgs-Doublet Model
arXiv 2608.30436 · 2026-09-01面向混合关键度片上系统的可扩展AXI4事务监控：从阶段级精度到ID级效率
Scalable AXI4 Transaction Monitoring for Mixed-Criticality SoCs: From Phase-Level Precision to ID-Level Efficiency
arXiv 2608.30435 · 2026-09-01介子引力D形因子与低能QCD中的对称性破缺
Meson gravitational D-form factors and symmetry breaking in low-energy QCD
arXiv 2608.30434 · 2026-09-01用于四旋翼飞行器不确定性感知系统辨识的混合PEM-GP框架
A Hybrid PEM-GP Framework for Uncertainty-Aware System Identification of Quadcopters
arXiv 2608.30433 · 2026-09-01一种基于PIV的物理信息表面压力重构方法
A Physics-Informed, PIV-Based Method for Surface Pressure Reconstruction
arXiv 2608.30432 · 2026-09-01泛化性是学习驱动动态系统的鲁棒性能特性
Generalization as a robust performance property of learning-enabled dynamical systems
arXiv 2608.30431 · 2026-09-01利用扩散磁共振成像（dMRI）对细胞级大脑微观结构进行成像
Imaging cellular-level brain microstructure with diffusion MRI
arXiv 2608.30430 · 2026-09-01EvoSkill注入：针对自进化智能体中自主技能生成与进化的红队测试
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
arXiv 2608.30429 · 2026-09-01我们能看见的谎言：具身社交交互中VLM智能体的联合言语与非言语欺骗
Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions
arXiv 2608.30428 · 2026-09-01截断上限的接受直方图揭示块扩散投机解码中的搁浅加速
Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding
arXiv 2608.30427 · 2026-09-01面向任务的对话系统中通过无监督微调学习推理与使用工具
Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems
arXiv 2608.30426 · 2026-09-01
