2026-09论文中文摘要
TAEC：面向多步视觉RAG的轨迹感知证据协调
TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
arXiv 2609.37349 · 2026-09-30DROM：一种语言引导的多技能机器人操作扩散框架
DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation
arXiv 2609.37348 · 2026-09-30全阳性编码下的INSIDE假设：解释与部分实证评估
The INSIDE assumption under all positive coding: interpretation and partial empirical assessment
arXiv 2609.37347 · 2026-09-30拓扑厚膜中扭结形状模式的遗迹——若干启示
Relic of the Kink Shape Mode in a Topological Thick Brane - some implications
arXiv 2609.37346 · 2026-09-30何时检索，何时保持：面向流式视频大语言模型的不确定性感知时间证据分配
When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs
arXiv 2609.37345 · 2026-09-30差分隐私下数据重建的尖锐转变
A Sharp Transition in Data Reconstruction under Differential Privacy
arXiv 2609.37344 · 2026-09-30分类作为搜索基础设施：类别创建、添加与清理如何影响知识检索
Classification as Search Infrastructure: How Category Creation, Addition and Cleanup Shape Knowledge Retrieval
arXiv 2609.37343 · 2026-09-30碰撞检测在生日阈值下是实例 $\widetilde{O}$ 最优的
Collision Detection is Instance $\widetilde{O}$ptimal Under the Birthday Threshold
arXiv 2609.37342 · 2026-09-30具有任意慢受控逃逸速率的Baker域
Baker domains with arbitrarily slow controlled rate of escape
arXiv 2609.37341 · 2026-09-30HyperSAM：用于高光谱遥感的可提示基础模型
HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing
arXiv 2609.37340 · 2026-09-30UGO：用于通用多目标跟踪的统一分割架构
UGO: Unified Architecture for General Multi-Object Tracking by Segmentation
arXiv 2609.37339 · 2026-09-30加权结构上一阶逻辑的保秩Gaifman范式
A Rank-Preserving Gaifman Normal Form for First-Order Logic on Weighted Structures
arXiv 2609.37337 · 2026-09-30整数上分数 $p$-拉普拉斯算子的最优 Hardy 不等式
Optimal Hardy Inequalities for Fractional $p$-Laplacians on the Integers
arXiv 2609.37336 · 2026-09-30带电电流准弹性中微子-原子核散射中可见运动学超标度变量的首次测量
First Measurement of the Superscaling Variable as a Function of Visible Kinematics in Charged-Current Quasi-Elastic Neutrino--Nucleus Scattering
arXiv 2609.37335 · 2026-09-30驯服机器人执行错误下的视觉-语言-动作策略：自补偿与压力测试
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
arXiv 2609.37334 · 2026-09-30合作、生态资源与适应性调控的三元系统动力学
Tripartite System Dynamics of Cooperation Ecological Resources and Adaptive Regulation
arXiv 2609.37333 · 2026-09-30乘法算术函数的截断自命距离
Truncated pretentious distances of multiplicative arithmetic functions
arXiv 2609.37332 · 2026-09-30OFBD：面向长尾学习的目标聚焦背景去偏
OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
arXiv 2609.37331 · 2026-09-30域是残差：适配自监督特征，而非生成器
The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators
arXiv 2609.37330 · 2026-09-30EntityWeaver：文档集合中命名实体关系的可视化探索与策管
EntityWeaver: Visual Exploration and Curation of Named-Entity Relationships in Document Collections
arXiv 2609.37329 · 2026-09-30CASR：面向多功能视频编码的内容自适应神经超分辨率后置滤波器，基于低秩过拟合
CASR: Content-Adaptive Neural Super-Resolution Post-Filter for Versatile Video Coding via Low-Rank Overfitting
arXiv 2609.37328 · 2026-09-30Koopman预测系数跟踪用于车载单站ISAC
Koopman-Predictive Coefficient Tracking for Vehicle-Mounted Monostatic ISAC
arXiv 2609.37327 · 2026-09-30不停歇地求解：小规模下的同策略蒸馏
Solving Without Stopping: On-Policy Distillation at Small Scale
arXiv 2609.37326 · 2026-09-30双曲格上依赖于边界条件的普适类
Boundary Condition dependent Universality Classes on a Hyperbolic Lattice
arXiv 2609.37325 · 2026-09-30VISTA：面向多模态情绪冲突的价值知情事件评估
VISTA: Value-Informed Event Appraisal for Multimodal Emotion Conflict
arXiv 2609.37324 · 2026-09-30并行回火用于基于扩散的组合优化
Parallel Tempering for Diffusion-Based Combinatorial Optimization
arXiv 2609.37323 · 2026-09-30Mubric：面向LLM评估的基于变异测试的评分标准生成
Mubric: Mutation Testing-Guided Rubric Generation for LLM Evaluation
arXiv 2609.37322 · 2026-09-30PowerMarketJax：面向电力市场的多智能体强化学习JAX基准套件
PowerMarketJax: A JAX Benchmark Suite for Multi-Agent Reinforcement Learning in Power Markets
arXiv 2609.37321 · 2026-09-30关于富碳和富氧热亚矮星的起源：一种 sdB 并合场景
On the origin of carbon- and oxygen-rich hot subdwarfs: an sdB merger scenario
arXiv 2609.37320 · 2026-09-30用于阱离子核自旋量子比特的磁场不敏感门组
A magnetic-field insensitive gate set for trapped-ion nuclear spin qubits
arXiv 2609.37318 · 2026-09-30接下来是什么？Omni-StoryBench：用于评估故事驱动的全模态生成的基准
What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generation
arXiv 2609.37317 · 2026-09-30面向激进四旋翼飞行的电池感知强化学习
Battery-Aware Reinforcement Learning for Aggressive Quadrotor Flight
arXiv 2609.37316 · 2026-09-30智能体基准测试是否名副其实？对使用工具的智能体环境的可执行契约审计
Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments
arXiv 2609.37315 · 2026-09-30FLASH：工业异常检测中合成异常生成的“一次生成，多次合成”框架
FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection
arXiv 2609.37314 · 2026-09-30磁$p$-Laplacian的谱几何
Spectral geometry of the magnetic $p$-Laplacian
arXiv 2609.37313 · 2026-09-30隐藏推理必然泄露，但未必可读：思维链监控的基本机遇与局限
Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring
arXiv 2609.37312 · 2026-09-30AutoMark：实现自动研究以发现更优的LLM水印
AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks
arXiv 2609.37310 · 2026-09-30稳定的丰沛向量丛不具有半正Kobayashi曲率
Stable ample vector bundles without semipositive Kobayashi curvature
arXiv 2609.37309 · 2026-09-30混合联合-选择性优化：低维感兴趣参数的降维Levenberg-Marquardt精化
Hybrid Joint-Selective Optimization: Reduced-Space Levenberg-Marquardt Refinement of Low-Dimensional Parameters of Interest
arXiv 2609.37308 · 2026-09-30记住你所做的：用于长视界视觉-语言-动作策略的动作历史记忆与双专家去噪
Remember What You Did: Action-History Memory with Dual-Expert Denoising for Long-Horizon Vision-Language-Action Policies
arXiv 2609.37307 · 2026-09-30面向通信的全息曲率可重构孔径的信道特性研究
Communication-Oriented Channel Characteristics of Holographic Curvature-Reconfigurable Apertures
arXiv 2609.37306 · 2026-09-30MetaCtrl：通过元认知控制器使大型语言模型推理更优且更简洁
MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller
arXiv 2609.37304 · 2026-09-30气相生长与表征：半导体MoS2上的范德瓦尔斯BiSbTeSe薄片
Vapor phase growth and characterization of van der Waals BiSbTeSe platelets on semiconducting MoS2
arXiv 2609.37303 · 2026-09-30技术说明：基于信息几何的零训练特征空间对齐
Technical note on: Zero-Training Feature-Space Alignment via Information Geometry
arXiv 2609.37302 · 2026-09-30奇偶扭转曲柄矩的代数与素数检测表达式
The Algebra of Parity-Twisted Crank Moments and a Prime-Detecting Expression
arXiv 2609.37301 · 2026-09-30离散四阶薛定谔方程的尖锐衰减估计
Sharp Decay estimates for the discrete Fourth-Order Schrödinger Equation
arXiv 2609.37300 · 2026-09-30交换耦合分子中自旋输运的原子尺度控制
Atomic-scale control of spin transport in exchange-coupled molecules
arXiv 2609.37299 · 2026-09-30扩展全共形图像分类器
Scaling Full Conformal Image Classifiers
arXiv 2609.37298 · 2026-09-30为什么跨骨骼重定向不可识别：生成运动模型的结构性限制
Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models
arXiv 2609.37297 · 2026-09-30超导量子比特中泄漏抑制交换门的参数化DRAG
Parametric DRAG for leakage-suppressed exchange gates in superconducting qubits
arXiv 2609.37296 · 2026-09-30
