2026-09论文中文摘要
时空中的局部多世界：Deutsch-Hayden描述符与局部波函数
Local Many Worlds in Spacetime: Deutsch-Hayden Descriptors and Local Wavefunctions
arXiv 2609.33453 · 2026-09-29洛伦兹量子宇宙学的维度（不）依赖性
Dimensional (In)dependence of Lorentzian Quantum Cosmology
arXiv 2609.33452 · 2026-09-29DAOCP：一种用于最优控制问题的对偶有效集求解器
DAOCP: a dual active set solver for optimal control problems
arXiv 2609.33451 · 2026-09-29原生关联：基于基础视觉语言模型的野外置信度感知人类感知
Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM
arXiv 2609.33450 · 2026-09-29历史手稿插图视觉分类数据集与模型评估
A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations
arXiv 2609.33449 · 2026-09-29标准模型中的三圈热质量
Thermal masses in the Standard Model at three loops
arXiv 2609.33448 · 2026-09-29从PDF到证据：面向临床实践指南的结构感知检索
From PDF to Evidence: Structure-Aware Retrieval for Clinical Practice Guidelines
arXiv 2609.33447 · 2026-09-29HESP：在本地 LLM 警报分流智能体中分离“探测什么”与“何时停止”
HESP: Separating What to Probe from When to Stop in Local LLM Alert-Triage Agents
arXiv 2609.33446 · 2026-09-29概念分数再学习：针对概念擦除的统一跨架构攻击
Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure
arXiv 2609.33445 · 2026-09-29阐明基于回归的扩散强化学习的设计空间
Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning
arXiv 2609.33444 · 2026-09-29上下文跨越：全双工语音模型与外部LLM后端之间的通信框架
Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backends
arXiv 2609.33443 · 2026-09-29Landau--Ginzburg 镜像对称性对于 ADE 奇点
Landau--Ginzburg mirror symmetry for ADE singularities
arXiv 2609.33442 · 2026-09-29MIC：解释AI生成多模态虚假信息中图像与声明的不一致性
MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation
arXiv 2609.33441 · 2026-09-29MAC-Net：一种用于基于任务态fMRI建模认知功能的多任务深度学习框架
MAC-Net: A Multi-Task Deep Learning Framework for Modeling Cognitive Function From Task-Based fMRI
arXiv 2609.33440 · 2026-09-29Raven：可组合智能体智能的“驾驭之驾驭”
Raven: The Harness of Harnesses for Composable Agentic Intelligence
arXiv 2609.33439 · 2026-09-29Path2Spec：基于路径感知的大语言模型规格生成
Path2Spec: Path-Aware Specification Generation via Large Language Models
arXiv 2609.33438 · 2026-09-29SchemaMem：用于延迟状态检索的架构索引循环记忆
SchemaMem: Schema-Indexed Recurrent Memory for Delayed State Retrieval
arXiv 2609.33436 · 2026-09-29Berry--Esseen定理、LLT、Edgeworth展开及局部平稳马尔可夫链的大偏差
Berry--Esseen theorems, LLT, Edgeworth expansions, and large deviations for Locally Stationary Markov Chains
arXiv 2609.33435 · 2026-09-29Kalai--Kleitman 直径界的曲线路径改进
A Curved-Path Refinement of the Kalai--Kleitman Diameter Bound
arXiv 2609.33434 · 2026-09-29CORA：一种用于诊断查询改写下文本到音频检索边界鲁棒性的协议
CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations
arXiv 2609.33433 · 2026-09-29TC-ADA：语义分割的一次性主动域适应
TC-ADA: One-Shot Active Domain Adaptation for Semantic Segmentation
arXiv 2609.33432 · 2026-09-29MoGround：视觉-语言模型中模态干扰的测量与缓解
MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models
arXiv 2609.33431 · 2026-09-29APEX：一种用于智能体辅助生产调度的可扩展模型
APEX: An Extensible Model for Agent-Assisted Production Scheduling
arXiv 2609.33430 · 2026-09-29图引导的仓库环境构建
Graph-Guided Repository Environment Construction
arXiv 2609.33429 · 2026-09-29可穿戴活动记录与睡眠轨迹的时间图学习用于建模青少年晶体智力
Temporal Graph Learning of Wearable Actigraphy and Sleep Traces for Modelling Adolescent Crystallized Intelligence
arXiv 2609.33428 · 2026-09-29迈向可组合云-HPC-边缘AI平台的系统之系统集成
Toward System-of-Systems Integration for Composable Cloud-HPC-Edge AI Platforms
arXiv 2609.33427 · 2026-09-29TeacherGRPO：通过教师对齐弥合推理蒸馏中的能力差距
TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment
arXiv 2609.33426 · 2026-09-29温度周期性调制使热电发电机的功率输出翻倍
Temperature Periodic Modulation Doubles the Power Output of Thermoelectric Generators
arXiv 2609.33425 · 2026-09-29一种轻量级双层优化对齐自监督表示以增强任务特定学习
A Light Bilevel Refinement Aligns Self-Supervised Representations for Stronger Task-Specific Learning
arXiv 2609.33424 · 2026-09-29静息态功能连接组的可解释深度学习揭示青少年智力的网络生物标志物
Explainable Deep Learning of Resting-State Functional Connectomes Reveals Network Biomarkers of Adolescent Intelligence
arXiv 2609.33422 · 2026-09-29嵌套递推的Padovan自动机描述
A Padovan-automatic description of a nested recurrence
arXiv 2609.33421 · 2026-09-29从矩恢复测度的低维半代数支集
Recovering Lower-Dimensional Semialgebraic Support of a Measure from its Moments
arXiv 2609.33420 · 2026-09-29高维白噪声的自适应 $L_2$ 型检验
An adaptive $L_2$-type test for high-dimensional white noise
arXiv 2609.33418 · 2026-09-29将记忆摘要基于效用意图
Grounding Memory Summarization in Utility Intent
arXiv 2609.33417 · 2026-09-29探究k-NN预处理对开发图神经网络的影响：基于公平性的视角
Investigating the Effect of k-NN Preprocessing on Developing Graph Neural Networks: A Fairness-Based Perspective
arXiv 2609.33416 · 2026-09-29$(H_0,H_1)$-光滑与重尾噪声下的加速随机方法
Accelerated Stochastic Method under $(H_0,H_1)$-Smoothness and Heavy-Tailed Noise
arXiv 2609.33415 · 2026-09-29TTRSD：视觉语言模型的测试时强化学习与自蒸馏
TTRSD: Test-Time Reinforcement Learning with Self-Distillation for Vision-Language Models
arXiv 2609.33414 · 2026-09-29怪异机器合成器：在表达式层利用AI编排
Weird Machine Compositors: Exploiting AI Orchestration at the Expression Layer
arXiv 2609.33413 · 2026-09-29解决状态表示不匹配：面向开环VLA规划的状态空间视觉推理
Resolving State-Representation Mismatch: State-Space Visual Reasoning for Open-Loop VLA Planning
arXiv 2609.33412 · 2026-09-29MetaBench-Harness：解锁基准测试框架的端到端优化
MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses
arXiv 2609.33411 · 2026-09-29FoldAttention：声明式参考Softmax实现快速解码与确定性反向传播
FoldAttention: Declared-Reference Softmax for Fast Decode and Deterministic Backward
arXiv 2609.33410 · 2026-09-29稠密并非足够：面向长程在线策略蒸馏的分层监督分配
Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation
arXiv 2609.33409 · 2026-09-29StarBOA：ISAC网络中稀疏雷达微多普勒的实时Mamba状态空间展开
StarBOA: Real-Time Mamba State-Space Unrolling for Sparse Radar Micro-Doppler in ISAC Networks
arXiv 2609.33408 · 2026-09-29基于对称思想的时滞次扩散方程若干新数值格式
Some new numerical schemes for delay sub-diffusion equations via the idea of symmetry
arXiv 2609.33406 · 2026-09-29自回归预训练中令牌角色的解耦
Decoupling Token Roles in Autoregressive Pretraining
arXiv 2609.33405 · 2026-09-29DataMagic：通过声明式多智能体编排创作数据视频
DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration
arXiv 2609.33403 · 2026-09-29VaME：探索多模态嵌入的变分潜在推理
VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings
arXiv 2609.33402 · 2026-09-29分组选择性状态空间滤波用于准确且流式的动作边界检测
Groupwise Selective State-Space Filtering for Accurate and Streaming Action Boundary Detection
arXiv 2609.33400 · 2026-09-29COEVO：递归自我改进的上下文与参数协同进化
COEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement
arXiv 2609.33398 · 2026-09-29CoViST：通过可组合状态进行视觉令牌压缩
CoViST: Visual Token Compression via Composable States
arXiv 2609.33397 · 2026-09-29
