2026-09论文中文摘要
具有近最优性能的单形反码的高效多项式时间解码
Efficient Polynomial-Time Decoding of Simplicial Anticodes with Near-Optimal Performance
arXiv 2608.29631 · 2026-09-01非对称Kuramoto网络中舞蹈平衡点的存在性与稳定性
Existence and Stability of Dancing Equilibria in Asymmetric Kuramoto Networks
arXiv 2608.29630 · 2026-09-01统计的领导力是什么？人工智能之后的统计学
Statistical Leadership of What? Statistics After AI
arXiv 2608.29629 · 2026-09-01用于约束优化的互流形退火KKT流：在非凸交流最优潮流中的应用
Reciprocal-Manifold Annealed KKT Flows for Constrained Optimization: Application to the Nonconvex AC Optimal Power Flow
arXiv 2608.29628 · 2026-09-01阿贝尔陈-西蒙斯理论中的真实多熵：通用链态的精确键环坍缩及其破缺
Genuine Multi-Entropy in Abelian Chern--Simons Theory: Exact Key-Ring Collapse and Its Breakdown for Generic Link States
arXiv 2608.29627 · 2026-09-01SPLG-Mamba：用于光学遥感图像显著目标检测的结构保持型局部-全局Mamba网络
SPLG-Mamba: Structure-Preserving Local-Global Mamba Network for Salient Object Detection in Optical Remote Sensing Images
arXiv 2608.29626 · 2026-09-01基于惩罚最小二乘的一步组因子分析
One-step group factor analysis via penalized least squares
arXiv 2608.29625 · 2026-09-01PrivBench：用于评估文本到文本私有化的整体模块化基准测试平台
PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization
arXiv 2608.29624 · 2026-09-01MI-Distillation：从模型插值的指令推理数据频谱中选择以进行思维链蒸馏
MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation
arXiv 2608.29623 · 2026-09-01AgenticRag-R1：用于多步推理、检索与记忆的带栈式记忆的智能体强化学习
AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
arXiv 2608.29622 · 2026-09-01CineForge：用于长时序视频生成的自改进智能体
CineForge: Self-Improving Agents for Long-Horizon Video Generation
arXiv 2608.29621 · 2026-09-01基于知识蒸馏的鲁棒分布式多卫星大规模MIMO传输
Robust Decentralized Multi-Satellite Massive MIMO Transmission via Knowledge Distillation
arXiv 2608.29620 · 2026-09-01基于变分推断的带结构化依赖的自适应函数聚类
Adaptive Functional Clustering with Structured Dependence via Variational Inference
arXiv 2608.29619 · 2026-09-01多接入投机推理：上行链路还是下行链路？
Multi-Access Speculative Inference: Uplink or Downlink?
arXiv 2608.29618 · 2026-09-01优先记忆的事实核查：一种基于知识图谱的多智能体虚假信息检测系统
Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection
arXiv 2608.29617 · 2026-09-01通过生存分析实现临床测量值的预后等效映射
Prognosis-equivalent mapping of clinical measurements via survival analysis
arXiv 2608.29614 · 2026-09-01用于大语言模型情感检测的跨语言功能向量
Cross-lingual Functional Vectors for Emotion Detection in Large Language Models
arXiv 2608.29613 · 2026-09-01大语言模型（LLMs）进行解释，嵌入（Embeddings）进行组织，图（Graphs）浮现：智能体驱动的科学知识编译
LLMs Interpret, Embeddings Organize, Graphs Emerge: Agent-Driven Compilation of Scientific Knowledge
arXiv 2608.29612 · 2026-09-01观察变化，保持流畅：基于时空表示学习的无监督动作分割
See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning
arXiv 2608.29611 · 2026-09-01超越表面对齐：基于情境理解与生成控制的动态机制研究
Beyond Surface Alignment: Grounding the Dynamics of Situational Understanding and Generative Control in LLMs
arXiv 2608.29610 · 2026-09-01nnMNet：火星地形语义分割基准模型
nnMNet: Baseline for Martian Terrain Semantic Segmentation
arXiv 2608.29609 · 2026-09-01广度学习：学习触及证据
Wide Learning: Learning to Reach Evidence
arXiv 2608.29608 · 2026-09-01SnapBench：面向移动交互的抓拍提问多模态检索基准测试
SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions
arXiv 2608.29607 · 2026-09-01Agent Zero Memory：面向大语言模型智能体的溯源感知长期记忆系统
Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents
arXiv 2608.29606 · 2026-09-01事后记忆-PRM：通过可审计的事后信用监督记忆管理
Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit
arXiv 2608.29605 · 2026-09-01RePair：将检索失败转化为反事实困难对
RePair: Turning Retrieval Failures into Counterfactual Hard Pairs
arXiv 2608.29604 · 2026-09-01随机顺序模型下的FirstFit在线着色算法
FirstFit online coloring in the random order model
arXiv 2608.29603 · 2026-09-01复杂参数的演化生成器
Evolution Generators for Complex Parameters
arXiv 2608.29602 · 2026-09-01面向多样化用户行为的排序策略的自适应双重鲁棒离线策略评估
Adaptive Doubly Robust Off-Policy Evaluation for Ranking Policies under Diverse User Behavior
arXiv 2608.29600 · 2026-09-01文本到视频扩散模型对硬件故障的鲁棒性研究
On the Resilience of Text-to-Video Diffusion Models to Hardware Faults
arXiv 2608.29598 · 2026-09-01择校中的可信度
Credibility in school choice
arXiv 2608.29597 · 2026-09-01GPT，反例生成器
GPT, the Counterexample Machine
arXiv 2608.29595 · 2026-09-01超越最小A型的德西特空间高自旋dS/CFT，以及德西特空间的双重性质
Higher-Spin dS/CFT beyond minimal type-A, and the doubled nature of de Sitter space
arXiv 2608.29594 · 2026-09-01自适应光学系统的自校准：应用于THEMIS太阳望远镜
Self-calibration of adaptive optics systems. Application to the THEMIS solar telescope
arXiv 2608.29593 · 2026-09-01利用单元探测下界分离解析表达式文法
Separating Parsing Expression Grammars using Cell-Probe Lower Bounds
arXiv 2608.29592 · 2026-09-01提问方式决定获取内容：基于理论的建议寻求型大语言模型对话中表达清晰度的测量
How You Ask Shapes What You Get: A Theory-Seeded Measurement of Articulation in Advice-Seeking LLM Conversations
arXiv 2608.29591 · 2026-09-01强安全护栏下大型视觉语言模型的护栏无关社会偏见评估
Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models
arXiv 2608.29590 · 2026-09-01并非对所有人安全：审计文本到图像安全流程中的方言惩罚
Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines
arXiv 2608.29589 · 2026-09-01自行调用邻居：带目标条件的同策略自蒸馏图游走
Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation
arXiv 2608.29588 · 2026-09-01分圆Iwasawa伪测度的布洛赫-正则元主部
Bloch-regulator Principal Parts of Cyclotomic Iwasawa Pseudomeasures
arXiv 2608.29587 · 2026-09-01分圆牛顿展开与秩一致的整数值牛顿完备化
Cyclotomic Newton Expansions and a Rank-Uniform Integer-Valued Newton Completion
arXiv 2608.29585 · 2026-09-01重新审视Auslander-Reiten-Serre对偶
Auslander-Reiten-Serre duality revisited
arXiv 2608.29584 · 2026-09-01驱动思考：VLA推理-轨迹一致性的运行时监测
Drive the Thoughts: Runtime Monitoring of VLA Reasoning-Trajectory Consistency
arXiv 2608.29583 · 2026-09-01SUP-MIMIC：用于评估大型语言模型对矛盾证据鲁棒性的多任务临床诊断基准
SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence
arXiv 2608.29582 · 2026-09-01连接智能体语义与现货容量：一种弹性且可恢复的服务模型
Bridging Agent Semantics with Spot Capacity: An Elastic and Recoverable Service Model
arXiv 2608.29581 · 2026-09-01用于Vlasov-Poisson-Fokker-Planck系统多尺度模拟的统一气体动理学波粒方法
Unified Gas-Kinetic Wave-Particle Method for Multiscale Simulation of Vlasov-Poisson-Fokker-Planck System
arXiv 2608.29580 · 2026-09-01预测不可预测之物：基于大语言模型的短期观测下长期混沌时间序列预测
Predicting the Unpredictable: LLM-powered Long-term Chaotic Time Series Forecasting under Short-term Observations
arXiv 2608.29579 · 2026-09-01选择导出的物品图的边谱：强边和弱边在协同过滤中编码不同的关系
The Edge Spectrum of Choice-Derived Item Graphs: Strong and Weak Edges Encode Different Relations in Collaborative Filtering
arXiv 2608.29578 · 2026-09-01TRINITY：面向个人风格视频精彩片段检测的多视角基准测试集
TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection
arXiv 2608.29577 · 2026-09-01计算延迟下网络化系统的事件触发控制与在线学习
Event-triggered Control and Online Learning for Networked Systems under Computational Delays
arXiv 2608.29576 · 2026-09-01
