2026-09论文中文摘要
学习发现有趣的数学
Learning to Discover Interesting Mathematics
arXiv 2609.28603 · 2026-09-25开发JPL统一验证与确认活动标准
Developing a Unified Verification and Validation Activity Standard at JPL
arXiv 2609.28600 · 2026-09-25BRFID：面向拜占庭鲁棒的联邦入侵检测
BRFID: Toward Byzantine-Robust Federated Intrusion Detection
arXiv 2609.28599 · 2026-09-25带边界几何对偶的4流形中曲面的光滑拓扑同痕
Smoothing topological isotopy of surfaces in 4-manifolds with a boundary geometric dual
arXiv 2609.28598 · 2026-09-25$f(T)$ 引力中Padé近似虫洞的光学与动力学特征
Optical and Dynamical Signatures of Padé Approximated Wormholes in $f(T)$ Gravity
arXiv 2609.28596 · 2026-09-25形如 $X^r(X^{q-1}+a)$ 的有限域上的置换二项式
Permutation binomials of the form $X^r(X^{q-1}+a)$ over finite fields
arXiv 2609.28595 · 2026-09-25迈向对 Erdős-Gyárfás 反例的更结构化搜索
Towards a more structured search for Erdős-Gyárfás counter-examples
arXiv 2609.28594 · 2026-09-25矢量活性物质中的边界与体相扰动
Boundary and bulk perturbations in vectorial active matter
arXiv 2609.28593 · 2026-09-25振幅阻尼信道的经典容量与纠缠代价
Classical Capacity and Entanglement Cost of the Amplitude Damping Channel
arXiv 2609.28592 · 2026-09-25TAM-Chain：基于吸收马尔可夫链与香农熵不确定性量化的多尺度甲状腺细胞学分类，用于假阴性抑制与域偏移适应
TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation
arXiv 2609.28590 · 2026-09-25OneTrans-V2：用一个Transformer统一工业推荐系统中的召回、粗排与精排
OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial Recommender
arXiv 2609.28589 · 2026-09-25面向大规模物联网的具有FBL上行链路和广播下行链路的感知辅助卫星回程
Sensing Assisted Satellite Backhaul with FBL UL and Broadcast DL for Massive IoT
arXiv 2609.28588 · 2026-09-25NumericJev：基于多路决策树的Jev类LLM数值解码
NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees
arXiv 2609.28587 · 2026-09-25智能体审批洗白：超出已批准调用的传递效应
Agent Approval Laundering: Transitive Effects Beyond the Approved Invocation
arXiv 2609.28586 · 2026-09-25持久可计费状态：工具调用LLM智能体中的拒绝钱包攻击与防御
Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents
arXiv 2609.28585 · 2026-09-25Fréchet 代数中 Michael 问题的一个解
A solution to Michael's problem for Fréchet algebras
arXiv 2609.28584 · 2026-09-25SGA：时间序列基础模型中多步预测的不确定性量化
SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models
arXiv 2609.28582 · 2026-09-25可审计性并非单一属性：强化学习中的规则重叠、行为一致性与组合
Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning
arXiv 2609.28581 · 2026-09-25Token聚类与语义序列Mamba用于高光谱图像分类
Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification
arXiv 2609.28580 · 2026-09-25AstroGenesis：面向天体物理研究的领域专用多智能体人工智能
AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research
arXiv 2609.28579 · 2026-09-25从智能电表数据揭示住宅光伏与电动汽车共同采用：负荷原型与检测用于需求侧规划
Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning
arXiv 2609.28578 · 2026-09-25ASR 集成用于语音匿名化器的音素可懂度评估
ASR ensembling for phoneme intelligibility evaluation of speech anonymizers
arXiv 2609.28577 · 2026-09-25理解数据修订的时间序列基础模型
Time-Series Foundation Models That Understand Data Revisions
arXiv 2609.28576 · 2026-09-25TWIST：一个针对对话记忆中干预质量提出的基准，并带有经人工验证的草稿对齐
TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment
arXiv 2609.28575 · 2026-09-25变更可证监管：政策变更下学习制品的治理
Change-Provenant Supervision: Governing Learned Artifacts Under Policy Change
arXiv 2609.28574 · 2026-09-25奇阶阿贝尔群上随机Cayley图的精确直径窗口
Exact Diameter Windows for Random Cayley Graphs on Odd-Order Abelian Groups
arXiv 2609.28573 · 2026-09-25网络智能体的困境：多阶段LLM智能体的瓶颈分析
Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents
arXiv 2609.28572 · 2026-09-25Ornstein-Uhlenbeck 半群极大算子在加权 $L^p$ 空间上的有界性
Ornstein-Uhlenbeck semigroup maximal operator on weighted $L^p$ space
arXiv 2609.28571 · 2026-09-25DEEPO：面向多模态大语言模型幻觉的双熵增强策略优化
DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs
arXiv 2609.28570 · 2026-09-25勘误及对“直径直径二性质的稳定性”的反例
Erratum and a counterexample to: Stability of diametral diameter two properties
arXiv 2609.28569 · 2026-09-25在无依赖栈上预训练和适配语言模型：从随机权重复现 GPT-2 124M（对照 llm.c），以及针对 Qwen3-0.6B 的临床适配器
Pretraining and adapting a language model on a dependency-free stack: GPT-2 124M from random weights, reproduced against llm.c, and a clinical adapter for Qwen3-0.6B
arXiv 2609.28568 · 2026-09-25316L不锈钢氢脆检测的防泄漏机器学习：SEM显微图像中纹理与深度特征的区域留出评估
Leakage-Safe Machine Learning for Hydrogen Embrittlement Detection in 316L Stainless Steel: A Region-Held-Out Evaluation of Texture and Deep Features in SEM Micrographs
arXiv 2609.28567 · 2026-09-25原始范数提取与三次费马方程的带符号下降
Primitive norm extraction and a signed descent for the cubic Fermat equation
arXiv 2609.28566 · 2026-09-25当解释无法被阅读：测量并纠正面向从右到左语言的SHAP和LIME渲染
When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages
arXiv 2609.28565 · 2026-09-25不要读日志：执行痕迹污染视频生成智能体中的验证器
Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents
arXiv 2609.28564 · 2026-09-25SpaFactor：用于组织学到转录组学推断的轻量级空间上下文感知基因程序建模
SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference
arXiv 2609.28563 · 2026-09-25矩阵聚合算子
Matrix Aggregation Operators
arXiv 2609.28562 · 2026-09-25CARE：用于扩散模型的条件感知表示正则化
CARE: Condition-Aware Representation Regularization for Diffusion Models
arXiv 2609.28561 · 2026-09-25随机大语言模型的投机式评估
Speculative Evaluation of Stochastic LLMs
arXiv 2609.28560 · 2026-09-25谁在操控执行框架？通过智能体行为对大型语言模型进行指纹识别
Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior
arXiv 2609.28559 · 2026-09-25压气机叶栅开口叶尖间隙流动的VAE潜空间自适应CFD修正
CFD Correction of Open Tip Clearance Flow in a Compressor Cascade Using VAE Latent Space Adaptation
arXiv 2609.28558 · 2026-09-25BaseCamp——一个用于自动化DNA测序数据管道的智能体AI框架
BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
arXiv 2609.28557 · 2026-09-25夸克子交叉框架下的有限温度轴子混合中子星
Finite-Temperature Axion-Admixed Neutron Stars in a Quarkyonic Crossover Framework
arXiv 2609.28555 · 2026-09-25Pistis 技术报告
Pistis Technical Report
arXiv 2609.28554 · 2026-09-25SMILESGNN：通过SMILES-图交叉注意力融合实现可解释的临床毒性预测
SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
arXiv 2609.28553 · 2026-09-25有限图上的渗流
Percolation on Finite Graphs
arXiv 2609.28552 · 2026-09-25一致归纳推断的序理论刻画
An Order-Theoretic Characterization of Consistent Inductive Inference
arXiv 2609.28551 · 2026-09-25图形离散性、Coxeter 加倍与广义多边形
Graphical Discreteness, Coxeter Doublings and Generalized Polygons
arXiv 2609.28550 · 2026-09-25女性董事能否提高ESG评级？一项元分析
Do Female Directors Raise ESG Ratings? A Meta-Analysis
arXiv 2609.28549 · 2026-09-25时间加权Besov空间中粗糙路径的直接方法
A Direct Approach to Rough Paths in Time-Weighted Besov Spaces
arXiv 2609.28548 · 2026-09-25
