2026-07论文中文摘要
将潜在思维链推理解释为动力系统
Interpreting Latent CoT Reasoning as Dynamical Systems
arXiv 2607.09698 · 2026-07-14安全响应很重要：输出感知安全护栏减轻多模态大语言模型中的过度拒绝
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
arXiv 2607.09697 · 2026-07-14缓解CTR模型早期训练崩溃
Mitigating Early Training Collapse in CTR Models
arXiv 2607.09696 · 2026-07-14FedCausal-Dyn：动态特征漂移下联邦学习的因果动态范式
FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift
arXiv 2607.09695 · 2026-07-14用于无训练语言模型推理的深度熵引导采样
Depth-Entropy Guided Sampling for Training-Free LLM Reasoning
arXiv 2607.09693 · 2026-07-14大语言模型中基于参考的蒸馏检测
Reference-Based Distillation Detection in LLMs
arXiv 2607.09692 · 2026-07-14编码智能体实际行动需要什么上下文？
What Context Does a Coding Agent Actually Need to Act?
arXiv 2607.09691 · 2026-07-14低自相关二进制序列问题中搜索空间区域的优先级划分
Prioritizing Search Space Regions in the Low Autocorrelation Binary Sequences Problem
arXiv 2607.09688 · 2026-07-14基于张量的模态分解与稀疏传感器布置用于布鲁日油田模拟模型
Tensor-Based Modal Decomposition and Sparse Sensor Placement for the Brugge Field Simulation Model
arXiv 2607.09687 · 2026-07-14MawForge：用于局部专家混合推理的内存受限专家实例化
MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference
arXiv 2607.09686 · 2026-07-14自适应多智能体系统中跨政策体系的迁移学习
Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems
arXiv 2607.09685 · 2026-07-14野外的科学机器学习：关于结构先验何时起作用及何时起反作用的诊断研究
SciML in the Wild: A Diagnostic Study of When Structural Priors Help and When They Hurt
arXiv 2607.09684 · 2026-07-14KV缓存压缩的消融、统计推断与验证
Ablation, Statistical Inference, and Validation for KV-Cache Compression
arXiv 2607.09683 · 2026-07-14AuditWeave：用于人工智能辅助和数据转换工作流程的防篡改、审计可导航证据层
AuditWeave: A Tamper-Evident, Auditor-Navigable Evidence Layer for AI-Assisted and Data-Transformation Workflows
arXiv 2607.09682 · 2026-07-14通过 *- 逆 P - 导数研究商环 R/P 的交换性
Commutativity of Factor Ring R/P via *-Reverse P-Derivations
arXiv 2607.09681 · 2026-07-14ECG-LDC：一种用于心电图心律失常分类的硬件高效低维计算框架
ECG-LDC: A Hardware-Efficient Low-Dimensional Computing Framework for ECG Arrhythmia Classification
arXiv 2607.09680 · 2026-07-14多方暗物质流体的晕结构和引力透镜特征
Halo structure and lensing signatures of a polytropic dark matter fluid
arXiv 2607.09679 · 2026-07-142026年伊朗战争中的精英代理、算法瓶颈和多平台信息级联
Elite Proxies, Algorithmic Bottlenecks, and Multi-Platform Information Cascades in the 2026 Iran War
arXiv 2607.09676 · 2026-07-14新闻与在线脱口秀广播中的性别差距分析
Gender Gap Analysis in News and Talk Online Radio Broadcast
arXiv 2607.09675 · 2026-07-14从工具到教师构建的队友：使用LearnAdapt智能工作室和PedOS 1.1 Lumina进行无代码教学插件创作
From Tools to Teacher-Built Teammates: No-Code Pedagogical Plugin Authoring with LearnAdapt Agentic Studio and PedOS 1.1 Lumina
arXiv 2607.09674 · 2026-07-14Critsly：用于设计教育和基于项目学习的人工制品感知人工智能批判队友
Critsly: An Artefact-Aware AI Critique Teammate for Design Education and Project-Based Learning
arXiv 2607.09673 · 2026-07-14格尔范德 - 多尔夫曼代数：幂零性、可解性、构造与分类
Gelfand--Dorfman Algebras: Nilpotency, Solvability, Construction and Classification
arXiv 2607.09672 · 2026-07-14完成欧几里得距离矩阵的哈达玛幂的秩恒等式
Completing the rank identity for Hadamard powers of Euclidean distance matrices
arXiv 2607.09671 · 2026-07-14在酉不变范数下，双中心矩阵对差异数据的通用最优性
Universal optimality of the double-centred matrix under unitarily invariant norms for dissimilarity data
arXiv 2607.09670 · 2026-07-14立场：每个真实数据都是人为构建，而非客观真理
Position: Every Ground Truth is a Human Construction, not an Objective Truth
arXiv 2607.09668 · 2026-07-14知识图谱与图神经网络：全面综述
Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
arXiv 2607.09666 · 2026-07-14格式敏感性指数：大语言模型基准测试中令牌控制的提示包装器稳健性与模式合规性
Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking
arXiv 2607.09665 · 2026-07-14从机器学习预测到使用论证的图尔敏模型提供信息丰富的诊断辅助
From ML Predictions to Informed Diagnostic Assistance Using the Toulmin Model of Argumentation
arXiv 2607.09664 · 2026-07-144DR360：用于4D雷达-相机全场景感知中联合3D检测和占用预测的状态推理
4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception
arXiv 2607.09629 · 2026-07-14用于热力学一致系统的广义斜梯度嵌入
Generalized skew-gradient embedding for thermodynamically consistent systems
arXiv 2607.09617 · 2026-07-14跨语言习语表达的概念网络：一种基于特征的图方法
Conceptual Networks for Cross-Linguistic Idiomatic Expressions: A Feature-Based Graph Approach
arXiv 2607.09576 · 2026-07-14按需定制的双向精细化器
Bidirectional Elaborators à la Carte
arXiv 2607.09564 · 2026-07-14PCPOP.jl：用于部分可交换多项式优化的Julia包
PCPOP.jl: A Julia package for partially commutative polynomial optimization
arXiv 2607.09339 · 2026-07-14柯西矩阵方案下的离散格尔季科夫 - 瓦诺夫模型及其高阶对应模型
Discrete Gerdjikov-Ivanov models and their higher-order counterparts from the Cauchy matrix scheme
arXiv 2607.09333 · 2026-07-14LongMedBench：用于长期临床决策的医疗智能体基准测试
LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making
arXiv 2607.09322 · 2026-07-14TNG上使用HARPS-N的GAPS计划LXXVII。存在冷木星时小近距行星的发生率
The GAPS Programme with HARPS-N at TNG LXXVII. Occurrence rates of small close-in planets in the presence of cold Jupiters
arXiv 2607.09320 · 2026-07-14用于全臂操作的触觉和视觉条件下的以接触为中心的控制
TACTIC: Tactile and Vision Conditioned Contact-Centric Control for Whole-Arm Manipulation
arXiv 2607.09218 · 2026-07-14事件突发触发器：基于事件的脉冲神经网络目标检测中的可用性后门攻击
Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection
arXiv 2607.09115 · 2026-07-14Dec-MARVEL：预算约束下无通信的去中心化多智能体探索
Dec-MARVEL: Decentralized Multi-Agent Exploration without Communication under Budget Constraints
arXiv 2607.09060 · 2026-07-14长视野终端基准测试：使用基于密集奖励的评分方式测试智能体在长视野终端任务中的极限
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
arXiv 2607.08964 · 2026-07-14AgenticFocus：从人类第一人称视角视频进行物体保留的混合现实合成，用于灵巧人形机器人学习
AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning
arXiv 2607.08857 · 2026-07-14部分可交换多项式优化
Partially-Commutative Polynomial Optimization
arXiv 2607.08841 · 2026-07-14装置的反击：动量守恒与空间叠加的代价
The Apparatus Strikes Back: Momentum Conservation and the Cost of Spatial Superpositions
arXiv 2607.08819 · 2026-07-14通过几何感知预训练增强上下文全景生成
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
arXiv 2607.08765 · 2026-07-14亚波长双各向异性谐振器产生的非对称高次谐波
Asymmetric high-harmonic generation from subwavelength bianisotropic resonators
arXiv 2607.08715 · 2026-07-14人工人
Artificial Persons
arXiv 2607.08695 · 2026-07-14对抗性不确定性下的鲁棒贝叶斯决策
Robust Bayesian Decision Making under Adversarial Uncertainty
arXiv 2607.08590 · 2026-07-14协议费用变化对自动化做市商流动性供应的因果效应
Causal Effects of Protocol-Fee Changes on Liquidity Provision in Automated Market Makers
arXiv 2607.08525 · 2026-07-14关于布劳威尔拉普拉斯猜想扩展的两个猜想
Proofs of two conjectures on generalizations of Brouwer's Laplacian conjecture
arXiv 2607.08452 · 2026-07-14分位数分布强化学习的统计效率与推断
Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning
arXiv 2607.08444 · 2026-07-14
