2026-09论文中文摘要
梯度引导的解耦自适应用于地理空间视觉-语言模型
Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models
arXiv 2609.32737 · 2026-09-29平面图中近最优分布式支配集
Near-Optimal Distributed Domination in Planar Graphs
arXiv 2609.32736 · 2026-09-29复杂生理系统中非线性动力学与混沌的表征与监测
Characterization and Monitoring of Nonlinear Dynamics and Chaos in Complex Physiological Systems
arXiv 2609.32735 · 2026-09-29REALIS：一个用于研究AI图像检测挑战的精选数据集
REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection
arXiv 2609.32734 · 2026-09-29商旗复形的数据结构
A data structure for quotient flag complexes
arXiv 2609.32733 · 2026-09-29Plan-to-Synthesis：基于语义潜流匹配的跨城市人类移动生成
Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching
arXiv 2609.32732 · 2026-09-29SkillVine：通过分支探索实现智能体技能进化
SkillVine: Agent Skill Evolution via Branching Exploration
arXiv 2609.32731 · 2026-09-29通过双锚定分布鲁棒优化利用目标信息的域适应
Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization
arXiv 2609.32730 · 2026-09-29重新审视随机凸优化中的AdaGrad：最后迭代、高概率与下界
Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds
arXiv 2609.32729 · 2026-09-29平面有向图上反馈顶点集的单指数算法
Single-Exponential Algorithms for Directed Feedback Vertex Set on Planar Digraphs
arXiv 2609.32728 · 2026-09-29分布鲁棒平均奖励强化学习：弱通信条件下的有限样本保证
Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weak Communication
arXiv 2609.32727 · 2026-09-29X射线脉冲星高吸积柱的脉冲轮廓
Pulse profiles of tall accretion columns in X-ray pulsars
arXiv 2609.32726 · 2026-09-29线性不等式约束下投影几何的极小极大选择
Minimax Choice of Projection Geometry under Linear Inequality Constraints
arXiv 2609.32725 · 2026-09-29彗星67P/Churyumov-Gerasimenko组分的吸积前辐照
Pre-accretional irradiation of comet 67P/Churyumov-Gerasimenko constituents
arXiv 2609.32724 · 2026-09-29相对可对偶性与缺陷的配边假设
Relative dualizability and the cobordism hypothesis for defects
arXiv 2609.32723 · 2026-09-29同族在线策略蒸馏的缩放性质
Scaling Properties of Same-Family On-Policy Distillation
arXiv 2609.32722 · 2026-09-29BiasReducer：奖励模型的自适应偏差缓解
BiasReducer: Adaptive Bias Mitigation for Reward Models
arXiv 2609.32720 · 2026-09-29非齐次Fourier空间中修正Navier--Stokes方程的爆破
Blow-Up of Modified Navier--Stokes Equations in Nonhomogeneous Fourier Spaces
arXiv 2609.32719 · 2026-09-29Hájek卷积定理的二阶扩展及其统计应用
A Second-Order Extension of Hájek's Convolution Theorem with Statistical Applications
arXiv 2609.32718 · 2026-09-29LLM对齐——语义保持变换下的效用不对称性
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
arXiv 2609.32717 · 2026-09-29区域-局部Copula证据融合用于异构遥感变化检测
Region-Local Copula Evidence Fusion for Heterogeneous Remote Sensing Change Detection
arXiv 2609.32716 · 2026-09-29基于夹捏天线的安全近场ISAC：利用相长-相消干涉
Secure Near-Field ISAC with Pinching-Antenna Systems: Exploiting Constructive-Destructive Interference
arXiv 2609.32715 · 2026-09-29$^{21}$B共振态的结构与衰变
Structure and decay of $^{21}$B resonances
arXiv 2609.32714 · 2026-09-29非正则无界记忆链的经验熵与转移熵的集中性
Concentration of empirical entropy and transfer entropy for non-regular chains with unbounded memory
arXiv 2609.32713 · 2026-09-29MassAlloc 注意力：让注意力自行分配其计算量
MassAlloc Attention: Let Attention Allocate Its Own Compute
arXiv 2609.32712 · 2026-09-29ProDyGS：来自单个静态单目相机的动态高斯泼溅
ProDyGS: Dynamic Gaussian Splatting from a Single Static Monocular Camera
arXiv 2609.32711 · 2026-09-29非凸多物种球面自旋玻璃的自由能
Free energy of non-convex multi-species spherical spin glasses
arXiv 2609.32710 · 2026-09-29耦合参变振荡器中的精确高斯纠缠动力学与初态控制
Exact Gaussian Entanglement Dynamics and Initial-State Control in Coupled Parametric Oscillators
arXiv 2609.32709 · 2026-09-29基于非平衡最优传输的一步生成建模
One-Step Generative Modeling via Unbalanced Optimal Transport
arXiv 2609.32708 · 2026-09-29Ti3AlC2中位点选择性钇取代实现Ti3C2Tx正极的层间工程与锂传输，用于高功率储能
Site-Selective Yttrium Substitution in Ti3AlC2 Enables Interlayer Engineering and Li Transport in Ti3C2Tx cathodes for High-Power Energy Storage
arXiv 2609.32707 · 2026-09-29学习引用：面向隐私感知语言模型的客户端解析生成
Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Models
arXiv 2609.32706 · 2026-09-29DPAMixerSR：一种高效的退化模式感知图像超分辨率模型
DPAMixerSR: An Efficient Degradation-Pattern-Aware Model for Image Super-Resolution
arXiv 2609.32705 · 2026-09-29CoWindow Attention：完全因果覆盖是一种集体属性
CoWindow Attention: Full Causal Coverage Is a Collective Property
arXiv 2609.32704 · 2026-09-29指数映射毛发的非解析性
Non-analyticity of hairs of exponential maps
arXiv 2609.32703 · 2026-09-29灰体因子与量子修正黑洞的霍金辐射谱
Greybody Factors and Hawking Spectra of Quantum-Corrected Black Holes
arXiv 2609.32702 · 2026-09-29CAIRN：用于多智能体探索的动态事实-意图DAG
CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration
arXiv 2609.32700 · 2026-09-29RandSlot：利用随机软标记学习紧凑的视觉文档表示
RandSlot: Learning Compact Visual Document Representations with Random Soft Tokens
arXiv 2609.32699 · 2026-09-29SEES：一种通过失败引导的VLA策略自适应演化的具身系统
SEES: A Self-Evolving Embodied System via Failure-Guided VLA Policy Adaptation
arXiv 2609.32698 · 2026-09-29严格凸函数和双曲函数的水平集估计
Level set estimates for strictly convex and hyperbolic functions
arXiv 2609.32697 · 2026-09-29平坦共识扩散：在噪声评估器下实现稳健的数据重塑
Flat-Consensus Diffusion for Robust Data Reshaping under Noisy Evaluator
arXiv 2609.32696 · 2026-09-29高斯ReLU网络的仿射几何：基于条件Kac-Rice公式
Affine Geometry of Gaussian ReLU Networks via Conditional Kac-Rice Formulas
arXiv 2609.32695 · 2026-09-29IGSD：用于搜索智能体的环境验证后见自蒸馏
IGSD: Environment-Verified Hindsight Self-Distillation for Search Agents
arXiv 2609.32694 · 2026-09-29带漂移的协作椭圆系统主特征值的奇异性分析
Singular analysis of the principal eigenvalue for cooperative elliptic systems with drifts
arXiv 2609.32693 · 2026-09-29世界智能体：语言模型能否让世界持续运行？
World Agent: Can Language Models Keep a World Running?
arXiv 2609.32692 · 2026-09-29智能体安全评估中的静默失败：用于间接提示注入下工具调用中介的验证性测试平台
Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection
arXiv 2609.32691 · 2026-09-29MM-OPD：迈向感知与推理之间的又一个瓶颈
MM-OPD: Towards One More Bottleneck Between Perception and Reasoning
arXiv 2609.32690 · 2026-09-29自进化时间序列预测智能体：基于情景记忆与在线策略学习
Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning
arXiv 2609.32689 · 2026-09-29最大平均度约束下重着色图的直径
The diameter of recoloring graphs under a maximum average degree bound
arXiv 2609.32688 · 2026-09-29带固定交易成本的制度切换布朗风险模型中的最优再保险-分红策略：脉冲控制问题的粘性解
Optimal Reinsurance-Dividend Strategy with Fixed Transaction Costs in a Regime-Switching Brownian Risk Model: A Viscosity Solution to the Impulse Control Problem
arXiv 2609.32686 · 2026-09-29PINNMorph：物理信息神经网络的在线自适应策略演化
PINNMorph: Evolving Online Adaptation Policies for Physics-Informed Neural Networks
arXiv 2609.32685 · 2026-09-29
