2026-07论文中文摘要
多状态模型的多级网络荟萃回归：来自个体和汇总证据的人群调整联合合成进展和生存数据
Multilevel network meta-regression for multistate models: Population-adjusted joint synthesis of progression and survival data from individual and aggregate evidence
arXiv 2607.25120 · 2026-07-31满足熵条件的有源通量型方法的构造
Construction of entropy satisfying Active Flux-type methods
arXiv 2607.25111 · 2026-07-31芳香吸附质在稀有气体纳米颗粒上的超快构型变化与反常扩散
Ultrafast configuration changes and anomalous diffusion of an aromatic adsorbate on rare-gas nanoparticles
arXiv 2607.24974 · 2026-07-31面积近似的极值问题
Extremal problem of area approximation
arXiv 2607.24828 · 2026-07-31SourceMinds参与2026年CheckThat!：多智能体管道中基于自然语言推理的引用审核用于完整事实核查文章生成
SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation
arXiv 2607.24802 · 2026-07-31无需读者的阅读：大语言模型将阅读和写作合并为一个纠缠的代码
Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code
arXiv 2607.24797 · 2026-07-31SpecPrefetch：用于稀疏混合专家基础模型的参数高效专家预取
SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models
arXiv 2607.24787 · 2026-07-31重新思考策略性扩散蒸馏中的无分类器引导
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
arXiv 2607.24731 · 2026-07-31基于持久上同调的密度鲁棒球坐标
Density-Robust Spherical Coordinates from Persistent Cohomology
arXiv 2607.24650 · 2026-07-31从机器学习到大规模地球观测产品：制作地图的最佳实践
From Machine Learning to Large-Scale EO Products: Best Practices for Making Maps
arXiv 2607.24532 · 2026-07-31去偏机器学习：识别、估计与形状约束
Debiased Machine Learning: Identification, Estimation, and Shape Constraints
arXiv 2607.24472 · 2026-07-31准确性掩盖了语言模型的失败方式：在匹配输出预算下测量失败状态
Accuracy Hides How Language Models Fail: Measuring Failure States Under Matched Output Budgets
arXiv 2607.24268 · 2026-07-31LU-500：用于概念遗忘的标志基准
LU-500: A Logo Benchmark for Concept Unlearning
arXiv 2607.24101 · 2026-07-31磁纹理缠绕控制相互作用的p波磁线中的费米子奇偶性开关
Magnetic-texture winding controls fermion-parity switches in an interacting $p$-wave magnet ring
arXiv 2607.24038 · 2026-07-31LeapBot-WA：通过预测性潜在对齐实现的世界锚定动作模型
LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments
arXiv 2607.23969 · 2026-07-31黄金分割猜想在十四元情况下成立
Balance Constants, Majority Cycles, and the Gold Partition Conjecture through Fourteen Elements
arXiv 2607.23926 · 2026-07-31在线主成分分析中的相变取决于$n/d\log(d)$，而非$n/d$
The Phase Transition in Online PCA Depends on $n/d\log(d)$, not $n/d$
arXiv 2607.23914 · 2026-07-31夹角为arccos(1/5)和arccos(3/5)的双角线
Biangular lines with angles arccos(1/5) and arccos(3/5)
arXiv 2607.23897 · 2026-07-31费米能级介导的氧化物陶瓷快速烧结加速
Fermi-level mediated acceleration of flash sintering of oxide ceramics
arXiv 2607.23383 · 2026-07-31通过收缩锚定稳定深度重建算子
Stabilizing Deep Reconstruction Operators with Contractive Anchoring
arXiv 2607.23341 · 2026-07-31CachedSearch：用于视频扩散测试时搜索的免训练缓存探索
CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion
arXiv 2607.23159 · 2026-07-31基于时间分辨偏振各向异性测量的中性稀有气体团簇尺寸表征
Size characterization of neutral rare-gas clusters based on time-resolved polarization anisotropy measurements
arXiv 2607.23064 · 2026-07-31智能体团队工作区：面向长期存在的编码智能体团队的自动化持久工作区
Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams
arXiv 2607.22917 · 2026-07-31群的团复形与序层
Clique complexes of groups and order sheaves
arXiv 2607.22369 · 2026-07-31三人微分博弈逻辑
Three-player Differential Game Logic
arXiv 2607.22359 · 2026-07-31AgentHOI：通过隐式表示对齐进行人类-物体交互视频生成的多智能体推理
AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment
arXiv 2607.22241 · 2026-07-31利用第五次引力波瞬变目录揭示双黑洞合并的四个亚群
Revealing Four Subpopulations of Binary Black-Hole Mergers with the Fifth Gravitational-Wave Transient Catalog
arXiv 2607.22011 · 2026-07-31“回家吧，副驾驶，你喝醉了”：理解开发者对智能体生成的代码审查评论的回应
"Go Home Copilot, You're Drunk": Understanding Developer Responses to Agent-Generated Code Review Comments
arXiv 2607.21997 · 2026-07-31人工智能红队评估能证明什么以及不能证明什么
What AI Red-Team Evaluations Can and Cannot Prove
arXiv 2607.21735 · 2026-07-31用于结构和语义一致的模拟到真实翻译的小波相位扩散
Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation
arXiv 2607.21628 · 2026-07-31奇数圈香农容量的改进下界
Improved lower bounds for the Shannon capacity of odd cycles
arXiv 2607.21517 · 2026-07-31PATS：用于智能体强化学习的策略感知训练框架
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
arXiv 2607.21419 · 2026-07-31用孔采维奇 - 西格尔 - 维滕准则选择复极值曲面
Selecting Complex Extremal Surfaces with the Kontsevich--Segal--Witten Criterion
arXiv 2607.21030 · 2026-07-31深度研究可靠吗？误导性知识会导致错误结论
Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions
arXiv 2607.20891 · 2026-07-31Sonic 舞台：自动生成交互式空间音景以促进盲人观众对对话视频的理解
Sonic Stage: Auto-Generating Interactive Spatial Soundscapes to Facilitate Dialogue Video Comprehension for Blind Viewers
arXiv 2607.20835 · 2026-07-31最小距离问题的精确指数
The sharp exponent for the minimal distance problem
arXiv 2607.20422 · 2026-07-31随机矩阵乘积算子范数的局部极限定理
Local limit theorem for the operator norm of products of random matrices
arXiv 2607.19873 · 2026-07-31实约化代数群的扎里斯基稠密子半群的强非算术性
Strong non-arithmeticity for Zariski dense subsemigroups
arXiv 2607.19841 · 2026-07-31轻子味混合矩阵的共形起源
The Conformal Origin of the Lepton Flavor Mixing Matrix
arXiv 2607.19454 · 2026-07-31带有奇异数的夸克物质星
Quarkyonic Stars with Strangeness
arXiv 2607.19220 · 2026-07-31文本模板令牌是扩散Transformer中的隐式语义寄存器
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
arXiv 2607.19139 · 2026-07-31优化遗憾值
Optimizing Regret
arXiv 2607.18866 · 2026-07-31密码分析基准测试：大语言模型能进行密码分析吗？
CryptanalysisBench: Can LLMs do Cryptanalysis?
arXiv 2607.18538 · 2026-07-31远程纠缠不一定是模块化囚禁离子量子计算的瓶颈
Remote entanglement need not be the bottleneck for modular trapped-ion quantum computing
arXiv 2607.18387 · 2026-07-31用RES-NOVA探测大质量分裂的非弹性暗物质
Probing large mass-splitting inelastic Dark Matter with RES-NOVA
arXiv 2607.18378 · 2026-07-31条纹序交变磁性
Stripe-Order Altermagnetism: Nematic Spin Splitting beyond the $l$-Wave Classification
arXiv 2607.17997 · 2026-07-31MagicSelector：通过反事实分解和渐进重排实现智能体工具选择的联合优化
MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
arXiv 2607.17751 · 2026-07-31FlexiGrad：用于分层细粒度分类的自适应梯度调制
FlexiGrad: Adaptive Gradient Modulation for Hierarchical Fine-Grained Classification
arXiv 2607.17563 · 2026-07-31用QQ等式审计大语言模型中的问题顺序效应：机制表征与饱和警告
Auditing Question-Order Effects in Large Language Models with the QQ Equality: Mechanism Characterization and a Saturation Caveat
arXiv 2607.17219 · 2026-07-31学习多模态内容的稀疏表示以增强冷启动项目推荐
Learning Sparse Representations of Multimodal Content for Enhanced Cold Item Recommendation
arXiv 2607.17184 · 2026-07-31
