2026-07论文中文摘要
T5-CSBoost：抗对抗扰动的语言模型指纹识别
T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting
arXiv 2607.14113 · 2026-07-17内省微调（IFT）：训练小型语言模型进行内省
Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect
arXiv 2607.14111 · 2026-07-17MAPS：在多智能体认知对话中建模共存的主观视角和共享意义
MAPS: Modeling Co-Existing Subjective Perspectives and Shared Meaning in Multi-Agent Cognitive Dialogue
arXiv 2607.14110 · 2026-07-17北极星：用于扩散语言模型高效推理的漂移感知缓存校准和令牌承诺
Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
arXiv 2607.14107 · 2026-07-17用于语言建模的令牌时间连续扩散
Token Time Continuous Diffusion for Language Modeling
arXiv 2607.14106 · 2026-07-17自动演化特定任务优化的提示指南
Automatically Evolving Prompt Guidelines for Task-Specific Optimization
arXiv 2607.14105 · 2026-07-17通过游戏学习乌兹别克语的UzWordnet和生成式人工智能
UzWordnet and Generative AI for Learning Uzbek by Game Playing
arXiv 2607.14104 · 2026-07-17语言模型智能体之间的潜在通信：通道、对齐方式及文本的局限性
Latent Communication Between Language Model Agents: Channels, Alignment, and the Limits of Text
arXiv 2607.14103 · 2026-07-17UniSAGE：用超结构统一静态和动态属性
UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure
arXiv 2607.14102 · 2026-07-17LBA：低查询预算下的文本硬标签对抗攻击
LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets
arXiv 2607.14101 · 2026-07-17用于阿拉伯语的量子组合自然语言处理：电路拓扑中的语法、形态学和词义
Quantum Compositional NLP for Arabic: Grammar, Morphology, and Word Sense in Circuit Topology
arXiv 2607.14100 · 2026-07-17只需持续提示：评估视觉语言模型中的重复苏格拉底式提示
Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs
arXiv 2607.14099 · 2026-07-17关于由标记树生成的局部有限超度量空间的柯尼希无穷引理
Konig's Infinity Lemma for locally finite ultrametric spaces generated by labeled trees
arXiv 2607.14098 · 2026-07-17基于交互的模型解释
IMEX Interaction-Based Model Explanation
arXiv 2607.14096 · 2026-07-17HG-RAG：用于结构化知识图谱的层次引导检索增强生成
HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
arXiv 2607.14095 · 2026-07-17一个非完全凸的完备、有界且几乎凸的度量空间
A Complete, Bounded and Almost Convex Metric Space which is Not Totally Convex
arXiv 2607.14094 · 2026-07-17用于自主无人机群搜索和救援的智能三级学习架构
Intelligent Three Level Learning Architecture for Autonomous UAV Swarms in Search and Rescue
arXiv 2607.14093 · 2026-07-17路径平均多项式压缩：多项式压缩、路径平均压缩和巴拿赫压缩的一种新推广
Path Averaged Polynomial Contractions: A New Generalization of Polynomial Contractions, Path-Averaged Contractions, and Banach Contractions
arXiv 2607.14092 · 2026-07-17人类感知、认知和决策动力学的模块化状态空间模型
A modular state-space model of human perception, cognition, and decision dynamics
arXiv 2607.14078 · 2026-07-17GitHub项目对智能编码工具的早期采用
Early Adoption of Agentic Coding Tools by GitHub Projects
arXiv 2607.14037 · 2026-07-17CF-Net：用于矛盾/犹豫识别的具有说话者归一化和确定性加权的冲突融合
CF-Net: Conflict Fusion with Speaker Normalisation and Certainty Weighting for Ambivalence/Hesitancy Recognition
arXiv 2607.13976 · 2026-07-17延迟促进自组装中的随机产率灾难
Stochastic Yield Catastrophe in Delay-Facilitated Self-Assembly
arXiv 2607.13902 · 2026-07-17PiVoT：一种用于在严重杂波下实时大规模多目标检测与跟踪的变分解决方案
PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
arXiv 2607.13891 · 2026-07-17AspectCLIP：通过方面引导的一致性正则化优化CLIP表示空间
AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization
arXiv 2607.13805 · 2026-07-17多图像胸部X光片分类中的前瞻性临床指征、事后报告泄露和融合设计：患者聚类评估
Prospective clinical indication, post-hoc report leakage, and fusion design in multi-image chest radiograph classification: a patient-clustered evaluation
arXiv 2607.13800 · 2026-07-17通过结构熵博弈实现全面、高效的大规模社区检测
Comprehensive, Efficient Large-Scale Community Detection via Structural Entropy Game
arXiv 2607.13713 · 2026-07-17二维电子系统中超越平均场的斯托纳转变：图解蒙特卡罗研究
Stoner transitions beyond mean-field in two-dimensional electronic systems: a diagrammatic Monte Carlo study
arXiv 2607.13675 · 2026-07-17量子计算机在粒子图像测速中的潜力
The potential of quantum computers for Particle Image Velocimetry
arXiv 2607.13641 · 2026-07-17磁外尔半金属中的涌现感应
Emergent induction in magnetic Weyl semimetals
arXiv 2607.13559 · 2026-07-17λPIC：一个以回调为中心的粒子模拟框架
$λ$PIC: A callback-centric particle-in-cell framework
arXiv 2607.13507 · 2026-07-17LAPO：多轮搜索推理中自生成过程奖励的留一回合归因
LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning
arXiv 2607.13501 · 2026-07-17玩还是不玩：从与ENOFLAG团队20年的CTF竞赛中获得的见解和经验教训
Poster: To Play or Not to Play: Insights and Lessons Learned from 20 Years of CTFs with ENOFLAG
arXiv 2607.13480 · 2026-07-17我们能操控黑箱吗？迈向以可控性为中心的协同代理推荐系统评估
Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents
arXiv 2607.13418 · 2026-07-17稳健拓扑振荡器控制向同步昼夜节律的可调相变
Robust topological oscillators govern a tunable phase transition to synchronized circadian rhythms
arXiv 2607.13322 · 2026-07-17将基于扩散的音乐合成模型应用于人类语音转换
Adapting Diffusion-Based Music Synthesis to Speech and Singing Voice Conversion
arXiv 2607.13278 · 2026-07-17极光DSQL：可扩展的多区域在线事务处理
Aurora DSQL: Scalable, Multi-Region OLTP
arXiv 2607.13276 · 2026-07-17momenTUM：一个用于设计、部署和探索生态瞬时评估研究的模式驱动平台
momenTUM: A schema-driven platform for designing, deploying, and exploring ecological momentary assessment studies
arXiv 2607.13076 · 2026-07-17在中子辐照钨中解耦应变速率敏感性和变形长度尺度效应：耦合纳米压痕、高分辨率电子背散射衍射和晶体塑性研究
Decoupling Strain-Rate Sensitivity and Deformation Length Scale Effects in Neutron-Irradiated Tungsten: A Coupled Nano-Indentation, HR-EBSD and Crystal Plasticity Study
arXiv 2607.12960 · 2026-07-17从2024年日全食图像序列测量内日冕的结构和动力学
Structure and Dynamics of the Inner Corona Measured from the DEB Initiative 2024 Eclipse Image Sequence
arXiv 2607.12950 · 2026-07-17利用大语言模型学习化学反应的机理推理
Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models
arXiv 2607.12771 · 2026-07-17由粘弹性细胞骨架介导的熵驱动起始和细胞摄取：基于昂萨格变分原理的动力学相图
Entropy-Driven Initiation and Cellular Uptake Mediated by Viscoelastic Cytoskeleton: A Kinetic Phase Diagram from Onsager Variational Principle
arXiv 2607.12766 · 2026-07-17非齐次随机图的重整化
Renormalisation of Inhomogeneous Random Graphs
arXiv 2607.12459 · 2026-07-17Ring-Zero：将零样本强化学习扩展到万亿参数以实现涌现推理
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
arXiv 2607.12395 · 2026-07-17通过等效变异检测命令式数据可视化库中的渲染错误
Detecting Rendering Bugs in Imperative Data Visualization Libraries via Equivalent Mutations
arXiv 2607.12363 · 2026-07-17VistaVLA：用于机器人操作的几何和语义感知3D高斯基础VLA
VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation
arXiv 2607.12356 · 2026-07-17哈密顿偏微分方程消失谱隙的有效稳定性
Effective stability for Hamiltonian PDEs vanishing spectral gaps
arXiv 2607.12270 · 2026-07-17如何实现递归式自我提升智能体与个人奇点：一种目标、范围、工具和基准驱动的多智能体架构
Self-Aware Recursively Self-Improving Agents for Personal Singularity: A Goal-, Scope-, Tool-, and Benchmark-Driven Multi-Agent Architecture
arXiv 2607.12254 · 2026-07-17方向准确性的真相：用于股票预测中LoRA适配的TimesFM的基准率诚实基准
When Directional Accuracy Lies: A Base-Rate-Honest Benchmark for LoRA-Adapted TimesFM on Equity Forecasting
arXiv 2607.12248 · 2026-07-17光学相干断层扫描中不确定性感知的多源视网膜液分割
Uncertainty-Aware Multi-Source Retinal Fluid Segmentation in OCT
arXiv 2607.12212 · 2026-07-17类氦和类锂离子中电子间相互作用的维希曼-克罗尔修正
Wichmann-Kroll Correction to the Interelectronic Interaction in He- and Li-Like Ions
arXiv 2607.12168 · 2026-07-17
