2026-10论文中文摘要
通过条件锚定蒸馏在持续学习中稳定语言模型
Stabilizing language models under continual learning via condition-anchored distillation
arXiv 2610.06940 · 2026-10-07当机器人崩溃时：在韦伯会议节点上的最优异步聚集
When Robots Crash: Optimal Asynchronous Gathering at Weber Meeting Nodes
arXiv 2610.06939 · 2026-10-07UniPro：通过传播实现从2D图像到3D体积的统一多模态医学图像分割
UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation
arXiv 2610.06938 · 2026-10-07FAPO：基于LUT的FPGA的扇出感知映射后优化
FAPO: Fanout-Aware Post-Mapping Optimization for LUT-Based FPGAs
arXiv 2610.06937 · 2026-10-07QiYao-I：一种基于流形的不规则多元时间序列预测基础模型
QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting
arXiv 2610.06936 · 2026-10-07均匀Bessel界：持久随机游走中的端点穿越
Uniform Bessel bounds for endpoint crossings in the persistent random walk
arXiv 2610.06935 · 2026-10-07暗物质混合中子星的半径与标度关系
Radii and Scaling Relations of Dark-Matter-Admixed Neutron Stars
arXiv 2610.06934 · 2026-10-07极小括号图中的三次顶点
Cubic vertices in minimal braces
arXiv 2610.06933 · 2026-10-07RADC：面向视觉-语言测试时自适应的风险感知双缓存
RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation
arXiv 2610.06932 · 2026-10-07递归熵风险强化学习在生成模型下的近最优样本复杂度
Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model
arXiv 2610.06931 · 2026-10-07多元函数数据异常检测的低秩与结构化稀疏张量分解
Low-Rank and Structured Sparse Tensor Decomposition for Anomaly Detection in Multivariate Functional Data
arXiv 2610.06930 · 2026-10-07物理孪生：利用幻影平台加速并实现机器人学习
Physical Twins: Accelerating and Enabling Robot Learning with Phantom Platforms
arXiv 2610.06929 · 2026-10-07视觉 Transformer 中抽象概念接地（Grounding）的转喻电路
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
arXiv 2610.06928 · 2026-10-07AttSVD：基于注意力引导的SVD实现提示自适应的低秩KV缓存压缩
AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD
arXiv 2610.06927 · 2026-10-07SWAP：面向视觉-语言-动作模型的逐步动作策略路由
SWAP: Stepwise Action Policy Routing for Vision-Language-Action Models
arXiv 2610.06926 · 2026-10-07从 $m$-堆除数尼姆中移除 $m$
Removing $m$ from $m$-pile Divisor Nim
arXiv 2610.06925 · 2026-10-07具有相互作用的流的复杂性与随机分析
Complexity of flows with interactions and stochastic analysis
arXiv 2610.06924 · 2026-10-07RadOnc-Agent：一个由LLM编排的放射治疗护理路径AI工作流框架
RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway
arXiv 2610.06923 · 2026-10-07多站点全天域红外相机阵列三角测量能力评估
An Assessment of the Triangulation Capabilities of a Multi-Site All-Sky Infrared Camera Array
arXiv 2610.06922 · 2026-10-07学习型修正器是否胜过简单回退？来自冻结VLA的证据
Does a Learned Corrector Beat a Simple Retreat? Evidence from a Frozen VLA
arXiv 2610.06921 · 2026-10-07扩展音乐标注模式：零样本预测还是少样本适应？
Extending Music Annotation Schemas: Zero-Shot Prediction or Few-Shot Adaptation?
arXiv 2610.06920 · 2026-10-07对比学习中的锚点散度用于语义几何
Anchor Divergence for Semantic Geometry in Contrastive Learning
arXiv 2610.06919 · 2026-10-07从不可靠轨迹中学习：对抗鲁棒的联邦Q学习
Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning
arXiv 2610.06918 · 2026-10-07FluidPD：面向SLO感知的预填充-解码分离LLM服务的原位弹性
FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving
arXiv 2610.06917 · 2026-10-07利用多波段数据对 NGC 6946 中 X 射线双星的分类
Classification of X-ray Binaries in NGC 6946 with the use of Multiwavelength Data
arXiv 2610.06916 · 2026-10-07无序进入关联：亚麦金太尔雪崩噪声的微观机制
Disorder into Correlation: A Microscopic Mechanism for Sub-McIntyre Avalanche Noise
arXiv 2610.06915 · 2026-10-07Text2Dashboard：面向企业DataBrain的自然语言仪表板生成受控代理架构
Text2Dashboard: A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain
arXiv 2610.06914 · 2026-10-07EDAP：一种用于无线传感器网络的高效数据收集协议
EDAP: An Efficient Data-Gathering Protocol for Wireless Sensor Networks
arXiv 2610.06911 · 2026-10-07GAMEGO：基于真实世界资产锚定的合成轨迹训练游戏开发智能体
GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets
arXiv 2610.06910 · 2026-10-07模群代数的单幂自同构与Lazard李代数的同调
Unipotent automorphisms of modular group algebras and the homology of the Lazard Lie algebra
arXiv 2610.06909 · 2026-10-07奇异摄动三物种Lotka--Volterra系统中的异宿环与长时间行为
Heteroclinic cycles and long-time behavior in a singularly perturbed three-species Lotka--Volterra system
arXiv 2610.06908 · 2026-10-07Lyapunov 正性与移动律随机-拟周期余圈的幺模判别准则
Lyapunov Positivity and Monodromy Criteria for Moving-Law Random--Quasiperiodic Cocycles
arXiv 2610.06907 · 2026-10-07正则图中彩虹 $k$-支配的复杂性、界与精确算法
Complexity, Bounds, and Exact Algorithms for Rainbow $k$-Domination in Regular Graphs
arXiv 2610.06906 · 2026-10-07ElecSafety：诊断大型语言模型对微控制器板的电气安全判断
ElecSafety: Diagnosing Large Language Model Safety Judgments for Microcontroller Boards
arXiv 2610.06905 · 2026-10-07稀疏Lévy图上的非局部哈密顿动力学：谱分析与多模态采样
Nonlocal Hamiltonian Dynamics on Sparse Lévy Graphs: Spectral Analysis and Multimodal Sampling
arXiv 2610.06904 · 2026-10-07Transformer 拒绝机制中的组件与维度稀疏性
Component and Dimension Sparsity in Transformer Refusal Mechanisms
arXiv 2610.06903 · 2026-10-07无需LLM摘要的树导航：长文档问答中分层检索的匹配成本研究
Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA
arXiv 2610.06902 · 2026-10-07气泡成核对脉动热管运行的影响：数值模拟研究
Impact of bubble nucleation on the functioning of the pulsating heat pipe: numerical simulation study
arXiv 2610.06901 · 2026-10-07ASAP：面向二进制反编译的汇编-源码对齐伪代码精炼
ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation
arXiv 2610.06900 · 2026-10-07小于1的树的拉普拉斯特征值个数
The number of Laplacian eigenvalues of trees less than one
arXiv 2610.06899 · 2026-10-07DIBench：在欺骗性注入下对基于GUI的移动智能体决策完整性的基准测试
DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections
arXiv 2610.06898 · 2026-10-07容量、响应性与对齐：什么使潜在结构具有可操作性
Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable
arXiv 2610.06897 · 2026-10-07医学图像对齐评估：前沿多模态模型通用视觉推理的测试
Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models
arXiv 2610.06896 · 2026-10-07一类具有连续时间的两性群体Volterra二次随机算子的解析解
Analytical solutions of one class of Volterra quadratic stochastic operators of a two-sex population with continuous time
arXiv 2610.06895 · 2026-10-07记忆预测超额：随机过程中预测增益与记忆长度的概率量
Memory Prediction Excess: A Probabilistic Quantity for Predictive Gain and Memory Length in Stochastic Processes
arXiv 2610.06894 · 2026-10-07dRGT大质量引力中卡西米尔虫洞的动力学稳定性与准正则模
Dynamical Stability and Quasinormal Modes of Casimir Wormholes in dRGT Massive Gravity
arXiv 2610.06893 · 2026-10-07对齐中线性奖励的公理可满足性
Axiom Satisfiability of Linear Rewards in Alignment
arXiv 2610.06892 · 2026-10-077-泛锦标赛的新上界
A New Upper Bound for 7-Universal Tournaments
arXiv 2610.06891 · 2026-10-07面向制造业的事件驱动ML流水线编排：AWS行业经验
Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience
arXiv 2610.06890 · 2026-10-07零样本可视化：利用用户提示轴探索文本语料库
Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes
arXiv 2610.06889 · 2026-10-07
