2026-07论文中文摘要
MyAG：一种用于设计和分析可组合大语言模型智能体系统的基于图的框架
MyAG: A Graph-Based Framework for Designing and Analyzing Composable LLM Agent Systems
arXiv 2607.13474 · 2026-07-16具有多频数据的三维随机障碍物的逆散射
Inverse scattering for three-dimensional random obstacles with multi-frequency data
arXiv 2607.13473 · 2026-07-16EgoHTR：以自我为中心的人类地形穿越的4D演示
EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal
arXiv 2607.13472 · 2026-07-16将音乐带入视野：音乐驱动的360°视频生成
Bring Music The Horizon: Music-Driven 360$^\circ$ Video Generation
arXiv 2607.13471 · 2026-07-16用于高能效集成感知与通信的后验置信度驱动波束成形
Posterior-Confidence Driven Beamforming for Energy-Efficient Integrated Sensing and Communication
arXiv 2607.13470 · 2026-07-16银行交易异常检测中的可解释人工智能：内部审计视角
Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective
arXiv 2607.13469 · 2026-07-16PQFA：用于多模态分类的融合表示的并行量子特征增强
PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Classification
arXiv 2607.13466 · 2026-07-16DevicesWorld：异构环境中跨设备智能体的基准测试
DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments
arXiv 2607.13465 · 2026-07-16通过半定规划对量子距离界协议进行安全性评估
Security evaluation of quantum distance-bounding protocols via semidefinite programming
arXiv 2607.13464 · 2026-07-16基于切线空间解缠的复合调制信号成分零样本识别
Compositional Zero-Shot Recognition based on Tangent Space Disentanglement for Composite Modulation Signals
arXiv 2607.13463 · 2026-07-16面向海洋物联网网络中集成传感与通信的能量最小化资源分配
Energy Minimization Oriented Resource Allocation for Integrated Sensing and Communication in Marine IoT Networks
arXiv 2607.13462 · 2026-07-16用于视觉与语言导航的联合在线与离线策略学习
Joint On-and-Off Policy Learning for Vision-and-Language Navigation
arXiv 2607.13461 · 2026-07-16LPM：工业规模的生成式视频修复
LPM: Industrial-Scale Generative Video Restoration
arXiv 2607.13460 · 2026-07-16埃尔顿：用于推理对抗性概率程序的瓮资源
Elton: Urn Resources for Reasoning about Adversarial Probabilistic Programs
arXiv 2607.13459 · 2026-07-16用于基于Transformer的场景文本识别的二维旋转位置嵌入
2D Rotary Position Embedding for Scene Text Recognition with Transformers
arXiv 2607.13458 · 2026-07-16实时古尔巴尼跟踪：锡克教基尔坦字幕的基准和参考系统
Live Gurbani Tracking: A Benchmark and Reference System for Captioning Sikh Kirtan
arXiv 2607.13457 · 2026-07-16TreeSRNF：用于树状3D对象几何和结构变异性生成建模的平方根法向场
TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects
arXiv 2607.13456 · 2026-07-16逆向推进：从逆向简单任务中进行遥操作成本有效的硬策略学习
Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks
arXiv 2607.13455 · 2026-07-16用于人工智能安全评估的对抗性提示框架
Adversarial Prompting Framework for AI Safety Assessment
arXiv 2607.13453 · 2026-07-16共生启发的知识蒸馏用于增量目标检测
Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
arXiv 2607.13452 · 2026-07-16学习用于可变形物体模拟的物理引导残差动力学
Learning Physics-Guided Residual Dynamics for Deformable Object Simulation
arXiv 2607.13451 · 2026-07-16发展中经济体智能无人机操作中的机器学习挑战
Machine Learning Challenges in Intelligent Unmanned Aerial Vehicle Operations in Developing Economie
arXiv 2607.13447 · 2026-07-16面向及超越百万自旋的光子伊辛机
Photonic Ising machines toward and beyond a million spins
arXiv 2607.13446 · 2026-07-16（扭曲）图幺半群的对合
Involutions of (twisted) diagram monoids
arXiv 2607.13445 · 2026-07-16数字主权的环境成本：全球南方主权人工智能基础设施的水、能源和排放影响
The Environmental Cost of Digital Sovereignty: Water, Energy, and Emissions Impacts of Sovereign AI Infrastructure in the Global South
arXiv 2607.13443 · 2026-07-16有限域上多项式的里奥丹阵列中的周期性
Periodicities in the Riordan arrays of polynomials over finite fields
arXiv 2607.13442 · 2026-07-16ReBound：用于交互式决策支持的重用感知隐私
ReBound: Reuse-Aware Privacy For Interactive Decision Support
arXiv 2607.13441 · 2026-07-16移动目标防御中的ε-不可区分性：框架、算法及云案例研究
ε-Indistinguishability In Moving Target Defense: Framework, Algorithms, And Cloud Case Studies
arXiv 2607.13440 · 2026-07-16DREA：用于仓库级漏洞检测的解耦推理与探索代理
DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection
arXiv 2607.13439 · 2026-07-16社会与影响异质性对社会 - 气候结果的影响
Impacts of social and impact heterogeneity on social-climate outcomes
arXiv 2607.13438 · 2026-07-16用于细粒度分类的CLIP引导无标签判别区域评分
CLIP-Guided Label-Free Discriminative Region Scoring for Fine-Grained Classification
arXiv 2607.13437 · 2026-07-16分布鲁棒且安全的模仿学习
Distributionally Robust and Safe Imitation Learning
arXiv 2607.13436 · 2026-07-16基于机器学习的原子核质量表的进一步探索
Further exploration of the machine-learning-based nuclear mass table
arXiv 2607.13435 · 2026-07-16哈伯德辅助下一维开放链中初贝-小本关联的稳定性
Hubbard-assisted stability of Hatsugai-Kohmoto correlations in a one-dimensional open chain
arXiv 2607.13434 · 2026-07-16当评分标准改变时：批判性思维作文评分的跨评分标准泛化
When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay Scoring
arXiv 2607.13433 · 2026-07-16局部冗余：一种基于合成记忆的可塑性信息论度量
Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
arXiv 2607.13432 · 2026-07-16探索用于生物医学数据到文本生成的小语言模型的训练后对齐：以药品说明书为例
Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet
arXiv 2607.13430 · 2026-07-16PUe：基于因果推断的有偏正无标记学习增强
PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
arXiv 2607.13428 · 2026-07-16江门中微子实验的低能量阈值和多信使触发系统
A Low-energy Threshold and Multi-messenger Trigger System for the JUNO Experiment
arXiv 2607.13427 · 2026-07-16水下声学超材料中由两个面内伪磁场诱导的手性朗道能级
Chiral Landau levels induced by two in-plane pseudomagnetic fields in underwater acoustic metamaterials
arXiv 2607.13426 · 2026-07-16通过注意力头重新加权实现大语言模型的数据高效适应
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
arXiv 2607.13425 · 2026-07-16平面图和单位圆盘图的支配-打包比率
Domination-packing ratio for planar and unit disk graphs
arXiv 2607.13424 · 2026-07-16温度缩放还不够：人类标签分布下的校准差距
Temperature Scaling Is Not Enough: Calibration Gaps Under Human Label Distributions
arXiv 2607.13423 · 2026-07-16用复合脉冲抑制拉姆齐磁力测量中的失谐诱导偏差
Suppressing Detuning-Induced Bias in Ramsey Magnetometry with Composite Pulses
arXiv 2607.13422 · 2026-07-16ScanFocus：一种用于时空视频定位的从粗到细框架
ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
arXiv 2607.13421 · 2026-07-16OrDA：用于首页营销板块推荐的访问习惯正交解缠框架
OrDA: Orthogonal Disentanglement of Access Habits Framework for Homepage Marketing Block Recommendations
arXiv 2607.13420 · 2026-07-16由无序诱导能带展宽控制的稀 Cu-3d 合金中的电阻率
Resistivity in Dilute Cu-3d Alloys Governed by Disorder-Induced Band Broadening
arXiv 2607.13419 · 2026-07-16基于参数衍射的目标感知：建模、估计与基本极限
Parametric Diffraction-Based Object Sensing: Modeling, Estimation, and Fundamental Limits
arXiv 2607.13417 · 2026-07-16EXPLORE：使用语言模型进行引导搜索以生成模拟拓扑结构
EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Models
arXiv 2607.13416 · 2026-07-16MultiAnimate：用于可控多角色动画的统一框架
MultiAnimate: A Unified Framework for Controllable Multi-Character Animation
arXiv 2607.13415 · 2026-07-16
