2026-07论文中文摘要
变压器真的无所不能吗？论跨任务归纳偏差的兼容性
Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks
arXiv 2607.17624 · 2026-07-21用于分布式环境监测的可生物降解毫米级发光传感器——功能性小精灵尘埃
Biodegradable, Millimeter-Scale Light-Emitting Sensors for Distributed Environmental Monitoring-Functional Pixie Dust
arXiv 2607.17623 · 2026-07-21基于硬件模型检查的基于BTOR2的C程序验证
BTOR2-Based C Program Verification via Hardware Model Checking
arXiv 2607.17622 · 2026-07-21用于智能体内存优化的机制性注意力引导
Mechanistic Attention Guidance for Agent Memory Refinement
arXiv 2607.17621 · 2026-07-21PoLoRA：一种预处理正交化的LoRA优化器
PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer
arXiv 2607.17620 · 2026-07-21长期记忆中的不安全编码偏好：基于大语言模型的代码生成的安全风险
Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation
arXiv 2607.17619 · 2026-07-21通过超表面实现空间非局域性成像
Spatial nonlocality imaging via metasurface
arXiv 2607.17618 · 2026-07-21Betti-Whittaker周期在对偶性下的行为：变体与应用
Betti-Whittaker periods under duality: variations and applications
arXiv 2607.17617 · 2026-07-21共振：基于三级级联ASR-LLM-TTS架构的构音障碍异步实时语音转换系统
Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture
arXiv 2607.17615 · 2026-07-21神经状态空间模型的在线学习
Online learning of neural state-space models
arXiv 2607.17614 · 2026-07-21基于隐式神经表示的生成式多曝光融合粗到细框架
Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation
arXiv 2607.17611 · 2026-07-21语义色彩自然度破坏器：通过内容感知颜色先验防止非法图像上色
Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors
arXiv 2607.17610 · 2026-07-21芬斯勒引力中超越广义相对论极限的大质量致密星：对GW190814次级天体的一种可能解释
Massive Compact Stars Beyond the General Relativity Limit in Finslerian Gravity: A Possible Explanation for the GW190814 Secondary
arXiv 2607.17609 · 2026-07-21局部代数表示上的范数空间
Space of norms on locally algebraic representations
arXiv 2607.17605 · 2026-07-21移动机器人与行人交互中的稳定性和舒适性
Stability and Comfort in Mobile Robot-Pedestrian Interactions
arXiv 2607.17604 · 2026-07-21使用非侵入性电生理测量探索脑网络：方法与应用
Exploring Brain Networks Using Noninvasive Electrophysiological Measurements: Methods and Applications
arXiv 2607.17602 · 2026-07-21通过可靠性感知多引擎融合实现可靠的蛋白质-配体结合亲和力预测
Trustworthy Protein-Ligand Binding Affinity Prediction via Reliability-Aware Multi-Engine Fusion
arXiv 2607.17601 · 2026-07-21ConsiSpace：学习几何一致性对视频空间推理很重要
ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning
arXiv 2607.17599 · 2026-07-21长上下文智能体仅靠渐进式披露就够了吗？
Is Progressive Disclosure All You Need for Long-Context Agents?
arXiv 2607.17598 · 2026-07-21有向偏好依附网络中的空间依赖性
Spatial Dependence in Directed Preferential-Attachment Networks
arXiv 2607.17597 · 2026-07-21多元宇宙分析中用于多重性控制的E值
E-Values For Multiplicity Control In Multiverse Analysis
arXiv 2607.17596 · 2026-07-21压缩随机逼近的集中性和均方界：一种统一的基本方法
Concentration and Mean-Square Bounds for Contractive Stochastic Approximation: A Unified Elementary Approach
arXiv 2607.17595 · 2026-07-21CuCrZr热沉材料的辐照性能揭示了热核聚变反应堆面临的新挑战
CuCrZr heat-sink irradiation performance reveals new challenges for thermonuclear fusion reactors
arXiv 2607.17594 · 2026-07-21Miles：基于预训练模型的类增量学习的可扩展子空间度量学习
Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning
arXiv 2607.17593 · 2026-07-21SSTMark：鲁棒的免训练语义级语音水印
SSTMark: Robust Training-Free Semantic-Level Speech Watermarking
arXiv 2607.17592 · 2026-07-21更快更简单地遍历0/1多面体
Faster and simpler traversal of 0/1-polytopes
arXiv 2607.17590 · 2026-07-21基于约束张量分解的稀疏非均匀阵列AFDM ISAC系统目标感知
Constrained Tensor Decomposition-Based Target Sensing for Sparse Non-Uniform Array-Enabled AFDM ISAC Systems
arXiv 2607.17589 · 2026-07-21极化激元泵浦-探测光谱中无序诱导的暗态线形
Disorder-induced Dark States Line Shape in Pump-Probe Spectroscopy of Polaritons
arXiv 2607.17587 · 2026-07-21检测、归因、叙述：用于可解释的洗钱者识别的端到端管道
Detection, Attribution, Narration: An End-to-End Pipeline for Explainable Money Mule Identification
arXiv 2607.17586 · 2026-07-21复Banach空间中\(\mathcal{S}_\mathbb{B}^{*}(α)\)的Hankel、Fekete - Szegö和Zalcman泛函的精确估计
Sharp Estimates for Hankel, Fekete-Szegö and Zalcman Functionals for $\mathcal{S}_\mathbb{B}^{*}(α)$ in Complex Banach Spaces
arXiv 2607.17584 · 2026-07-21用于低频电场的单原子传感器
Single-atom sensor for low-frequency electric field
arXiv 2607.17583 · 2026-07-21大型图像集中可扩展的模型辅助多目标估计
Scalable Model-Assisted Multi-Target Estimation in Large Image Collections
arXiv 2607.17581 · 2026-07-21与多项式非调和振荡器相关的分数阶热半群的精确时间衰减估计
Sharp Time-Decay Estimates for Fractional Heat Semigroups Associated with Polynomial Anharmonic Oscillators
arXiv 2607.17580 · 2026-07-21整数集Z²在算子范数下是灵活稳定的
$\mathbb{Z}^2$ is flexibly stable in the operator norm
arXiv 2607.17578 · 2026-07-21pyHB：一种用于非线性动力学的开源自动微分增强半解析求解器
pyHB: an open-source automatic-differentiation-enhanced semi-analytical solver for nonlinear dynamics
arXiv 2607.17577 · 2026-07-21基于潜在想象的视觉四足导航预测训练
Predictive Training with Latent Imagination for Visual Quadruped Navigation
arXiv 2607.17574 · 2026-07-21使用 DW-HKEM 的抗量子银行交易安全：具有实时性的混合 RSA/ML-KEM 加密网关
Quantum-Resilient Banking Transaction Security using DW-HKEM: A Hybrid RSA/ML-KEM Cryptographic Gateway with Real-Time Monitoring
arXiv 2607.17573 · 2026-07-21浏览器中的万亿级查询处理：重新思考GPU加速
Terascale Query Processing in the Browser: Rethinking GPU Acceleration
arXiv 2607.17571 · 2026-07-21用于混合整数线性规划的全局注意力图变换器的Weisfeiler-Leman特征
A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs
arXiv 2607.17570 · 2026-07-21开放修改搜索的跨域加速：从商品平台到新兴内存和存储设备
Cross-Domain Acceleration of Open Modification Search: From Commodity Platforms to Emerging Memory and Storage Devices
arXiv 2607.17569 · 2026-07-21IllustrisTNG中跨尺度的本征多相气体-黑洞连接
The Intrinsic Multiphase Gas--Black Hole Connection across Scales in IllustrisTNG
arXiv 2607.17567 · 2026-07-21量子理论的几何方法。L-泛函
Geometric Approach to Quantum Theory. L-functionals
arXiv 2607.17566 · 2026-07-21ZifaMem：人工智能伴侣中用于人物形象、偏好和情感连续性的结构化记忆
ZifaMem: Structured Memory for Persona, Preference, and Emotional Continuity in AI Companions
arXiv 2607.17564 · 2026-07-21用于工程超导量子比特耗散的时间衍射光栅
Temporal Diffraction Grating for Engineered Superconducting Qubit Dissipation
arXiv 2607.17562 · 2026-07-21强化学习：从算法到基础模型
Reinforcement Learning: From Algorithms To Foundation Models
arXiv 2607.17560 · 2026-07-21COLIP-2：嗅觉-视觉-语言嵌入
COLIP-2: Olfaction-Vision-Language Embeddings
arXiv 2607.17559 · 2026-07-21为什么反馈增强的自蒸馏不能改进检索交织搜索智能体？
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?
arXiv 2607.17558 · 2026-07-21具有爱泼斯坦-津偏好的无限期不完全市场中的消费与投资
Consumption and Investment in Incomplete Markets with Epstein-Zin Preferences in Infinite Horizon
arXiv 2607.17557 · 2026-07-21超越自旋：QCD磁星
Beyond Spin: QCD Magnetars
arXiv 2607.17556 · 2026-07-21高频金融市场中基于波动率感知的极端事件检测
Volatility-Aware Extreme Event Detection in High-Frequency Financial Markets
arXiv 2607.17555 · 2026-07-21
