2026-09论文中文摘要
坦白你所知道的：大语言模型遗忘中的遗忘集与模型知识的错位
Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
arXiv 2609.00605 · 2026-09-02NeuroGraph：一种用于先进制造中可解释威胁推理的AI图驱动神经符号框架
NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing
arXiv 2609.00604 · 2026-09-02通用Beta入射角：柯西刚性与无限排列
Universal Beta Incidence Angles: Cauchy Rigidity and Infinite Arrangements
arXiv 2609.00603 · 2026-09-02一个非右三角化的右预三角化范畴
A right pretriangulated category which is not right triangulated
arXiv 2609.00602 · 2026-09-02双曲吸引子与扩张映射族中SRB熵泛函的行为
Behavior of the SRB Entropy Functional in Families of Hyperbolic Attractors and Expanding Maps
arXiv 2609.00601 · 2026-09-02动态对齐还是角持续性？
Dynamic Alignment or Angular Persistence?
arXiv 2609.00600 · 2026-09-02磁化哈密顿动力学的超临界平均场极限
Supercritical mean--field limit for magnetized Hamiltonian dynamic
arXiv 2609.00598 · 2026-09-02拓扑引导
Topological Steering
arXiv 2609.00597 · 2026-09-02采用精确线搜索的BFGS算法的最小Q阶为1
The Minimum Q-Order of BFGS with Exact Line Search Is One
arXiv 2609.00596 · 2026-09-02SoK：当安全智能体共同失效时：多智能体大语言模型（LLM）系统的安全性
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
arXiv 2609.00595 · 2026-09-02具有单纯Mori锥的雅可比椭圆曲面上的有界上同调性质
Bounded cohomology property on Jacobian elliptic surfaces with simplicial Mori cones
arXiv 2609.00592 · 2026-09-02CRAFT：原生AI 6G无线接入网中预可解释性的微调
CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN
arXiv 2609.00590 · 2026-09-02基于空间引力波探测中时延干涉测量通道的线性重组的定向响应优化
Directional Response Optimization through Linear Recombination of Time-Delay Interferometry Channels in Space-based Gravitational Wave Detection
arXiv 2609.00589 · 2026-09-02无限层La$_{0.8}$Sr$_{0.2}$NiO$_2$中压力增强且稳定的超导电性的微观起源
Microscopic Origin of Pressure-Enhanced and Robust Superconductivity in Infinite-Layer La$_{0.8}$Sr$_{0.2}$NiO$_2$
arXiv 2609.00586 · 2026-09-02实时神经形态频谱智能模拟器
Real-Time Neuromorphic Spectrum Intelligence Simulator
arXiv 2609.00585 · 2026-09-02Socrates went Nuclear：在学习情境中使用脑传感技术比较AI系统的交互策略
Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing
arXiv 2609.00584 · 2026-09-02无单色单位面积矩形的平面21着色
A 21-Coloring of the Plane Without Monochromatic Unit-Area Rectangles
arXiv 2609.00583 · 2026-09-02高自旋粒子的自旋密度矩阵
Spin density matrix for high-spin particles
arXiv 2609.00582 · 2026-09-02用大语言模型（LLM）和编程语言语义预测程序退出码
Predicting Program Exit Code with LLMs and Programming Language Semantics
arXiv 2609.00579 · 2026-09-02相同请求，不同边界：评估对话语境下的网络安全辅助能力
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
arXiv 2609.00578 · 2026-09-02GeoPAR：基于几何引导并行自回归学习的大规模多智能体组合优化
GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning
arXiv 2609.00577 · 2026-09-02无对齐的一致性：与随机不可区分的项目敏感型语言模型
Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random
arXiv 2609.00576 · 2026-09-02拓展三层Ruddlesden-Popper镍酸盐家族：Sm₄Ni₃O₁₀₋δ单晶的合成与表征
Expanding the trilayer Ruddlesden-Popper nickelate family: Synthesis and characterization of Sm$_4$Ni$_3$O$_{10-δ}$ single crystals
arXiv 2609.00574 · 2026-09-02黑洞时空中量子虚部的性能
Performance of quantum imaginarity in black hole spacetime
arXiv 2609.00573 · 2026-09-02企业AI中遗留系统、治理与决策完整性的数学框架
A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AI
arXiv 2609.00572 · 2026-09-02带颜色偏好的图着色
Graph Coloring with Color Preferences
arXiv 2609.00569 · 2026-09-02WiseSpec：面向代码生成的需求驱动智能体
WiseSpec: Requirements-Driven Agents for Code Generation
arXiv 2609.00568 · 2026-09-02特征p>0下的Hodge--Tate分裂与Akizuki--Nakano消失定理
Hodge--Tate splitting and Akizuki--Nakano vanishing in positive characteristic
arXiv 2609.00567 · 2026-09-02对齐但扁平化：分析大语言模型（LLM）中文化对齐与多样性之间的权衡
Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs
arXiv 2609.00565 · 2026-09-02弹涂鱼利用尾部推力辅助拐杖式运动，在不同湿度的泥地上移动
Mudskippers use tail thrusting to help crutching to move on mud of various wetness
arXiv 2609.00564 · 2026-09-02用于研究运动的泥浆强度控制、变化与表征的重要性及方法
Importance and methods to control, vary, and characterize mud strength for studying locomotion
arXiv 2609.00563 · 2026-09-02BiMTokenizer：通过双向状态空间建模在低比特率语音分词中保持语义-声学平衡
BiMTokenizer: Preserving Semantic-Acoustic Balance in Low-Bitrate Speech Tokenization via Bidirectional State-Space Modeling
arXiv 2609.00562 · 2026-09-02金子（Kaneko）的val函数的分布
Distribution of Kaneko's val function
arXiv 2609.00560 · 2026-09-02MIMO-OFDM ISAC系统的时延-多普勒感知性能分析
Delay-Doppler Sensing Performance Analysis for MIMO-OFDM ISAC Systems
arXiv 2609.00559 · 2026-09-02强耦合量子流体的等μ/T全息熵及其吸引子
Iso-$μ/T$ holographic entropy and its attractor for a strongly coupled quantum fluid
arXiv 2609.00558 · 2026-09-02临界指数小于1的可及CAT(-1)群
Accessible CAT$(-1)$ groups of critical exponent less than one
arXiv 2609.00557 · 2026-09-02基于势引导的粒子转向的否定约束灵巧抓取
Potential-Guided Particle Steering for Negation-Constrained Dexterous Grasping
arXiv 2609.00555 · 2026-09-02完全正映射的算子值极大f-散度
Operator-valued maximal $f$-divergences for completely positive maps
arXiv 2609.00554 · 2026-09-02核求积的谱界
Spectral Bounds for Kernel Quadrature
arXiv 2609.00553 · 2026-09-02面向抗掉队节点分布式计算的流形感知通用编码计算
Manifold-Aware General Coded Computing for Straggler-Resilient Distributed Computing
arXiv 2609.00552 · 2026-09-02EM^2Mem：面向大型语言模型的以事件为中心的多模态记忆
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
arXiv 2609.00551 · 2026-09-02相同语义，不同结果：知识冲突下多模态大语言模型的模态鲁棒性研究
Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict
arXiv 2609.00550 · 2026-09-02技能遵循：评估支持检索的大语言模型智能体的实际技能使用情况
Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents
arXiv 2609.00549 · 2026-09-02探戈节奏下的时间衰减向量搜索：联合建模语义相似度与时间新鲜度
Time-Decayed Vector Search in the Rhythm of TANGO: Jointly Modeling Semantic Similarity and Temporal Freshness
arXiv 2609.00548 · 2026-09-02用于高效概率最优潮流评估的贝叶斯自适应谱代理模型
A Bayesian Adaptive Spectral Surrogate Model for Efficient Probabilistic Optimal Power Flow Evaluation
arXiv 2609.00547 · 2026-09-02显而易见的仲费米子
Parafermions in plain sight
arXiv 2609.00545 · 2026-09-02GenONet：用于高分辨率临近降水预报的生成算子网络
GenONet: A Generative operator Network for High-Resolution Precipitation Nowcasting
arXiv 2609.00544 · 2026-09-02用于检索增强生成的文档关系图上的反馈辅助信任传播
Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation
arXiv 2609.00543 · 2026-09-02常压下重锶掺杂的La$_{2}$SrNi$_{2}$O$_{7-δ}$作为四方Ruddlesden-Popper相
Heavily Sr-Doped La$_{2}$SrNi$_{2}$O$_{7-δ}$ as a Tetragonal Ruddlesden-Popper Phase at Ambient Pressure
arXiv 2609.00542 · 2026-09-02无全额补偿加价的多区间调度最优统一定价
Optimal Uniform Pricing for Multi-Interval Dispatch without Make-Whole Uplifts
arXiv 2609.00541 · 2026-09-02
