2026-10论文中文摘要
AdaptViT：在定制RISC-V上的运行时自适应视觉Transformer部署
AdaptViT: Runtime-Adaptive Vision Transformer Deployment on Custom RISC-V
arXiv 2610.02288 · 2026-10-05费米子量子计算的预幺半范畴语义与可扩展图解
Premonoidal Semantics and Scalable Diagrammatics of Fermionic Quantum Computing
arXiv 2610.02287 · 2026-10-05BootLoops：一个由LLM驱动的精确定量科学工具包
BootLoops: an LLM-driven toolkit for exact quantitative science
arXiv 2610.02286 · 2026-10-05脉冲间隔变化对蝙蝠叫声深度学习分类的影响
Effects of interpulse-interval variation on deep-learning classification of bat vocalizations
arXiv 2610.02284 · 2026-10-05MuLoRA：面向持续学习的谱均衡低秩适配
MuLoRA: Spectrally Balanced Low-Rank Adaptation for Continual Learning
arXiv 2610.02283 · 2026-10-05具有正规转移算子的马尔可夫链的全局中心极限定理
Global Central Limit Theorems for Markov chains with normal transition operator
arXiv 2610.02282 · 2026-10-05AI风险观测站：从年报中的AI披露我们能学到什么关于社会韧性的启示？
The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?
arXiv 2610.02281 · 2026-10-05内禀电磁性质
Intrinsic electromagnetic properties
arXiv 2610.02280 · 2026-10-05通过边界态实现的破圈复形的局部壳化及Negami多项式的色特征化
Local Shellings of Broken-Circuit Complexes via Boundary States and the Chromatic Specialization of the Negami Polynomial
arXiv 2610.02279 · 2026-10-05CLEAN：概念空间扩展下基于架构隔离的心理测量学一致的增量认知诊断
CLEAN: Psychometrically Consistent Incremental Cognitive Diagnosis under Concept-Space Expansion via Architectural Isolation
arXiv 2610.02278 · 2026-10-05关于叶状复解析结构形变 II：Artin环函子
On deformations of foliated complex analytic structures II: Functors of Artin rings
arXiv 2610.02277 · 2026-10-05树上的贪心均匀性：精确障碍与近均匀蜘蛛图
Greedy Uniformity on Trees: Exact Obstruction and Near-Uniform Spiders
arXiv 2610.02276 · 2026-10-05AT-free、弦图与凸二分图上的最大边开打包
Maximum Edge Open Packing on AT-Free, Chordal, and Convex Bipartite Graphs
arXiv 2610.02275 · 2026-10-05Awomo-SimDataEngine：智能体式仿真就绪世界生成
Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation
arXiv 2610.02274 · 2026-10-05评论："预印本演变：arXiv 上未评审草稿的兴起及其对天文学的影响"
Comment on: "The Preprint Evolution: The Rise of Unreviewed Drafts on arXiv and its Implications for Astronomy"
arXiv 2610.02273 · 2026-10-05具有给定最大度数的谱极值连通非正则图的度序列：稠密情形
Degree sequences of spectrally extremal connected nonregular graphs with prescribed maximum degree: the dense case
arXiv 2610.02272 · 2026-10-05胸部X射线视觉语言模型的可靠性压力测试与决策时路由
Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models
arXiv 2610.02270 · 2026-10-05基于变分风险最小化的置信门控云-边级联分诊用于医学影像
Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging
arXiv 2610.02269 · 2026-10-05从数学证书到可执行证书的机器遗忘
From Mathematical to Executable Certificates for Machine Unlearning
arXiv 2610.02268 · 2026-10-05快速模型，缓慢证据：LLM智能体框架中System-1决策模型的配对与自我审计评估
Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
arXiv 2610.02267 · 2026-10-05Simpson-Visser 正则化下的量子 Oppenheimer-Snyder-Datt 黑洞
Simpson-Visser regularization of the quantum Oppenheimer-Snyder-Datt black hole
arXiv 2610.02266 · 2026-10-05事件引导的神经视频压缩
Event-guided Neural Video Compression
arXiv 2610.02265 · 2026-10-05除数之和的除数中的反链
Antichains among Divisor Sums of Divisors
arXiv 2610.02264 · 2026-10-05ZAGNet：用于患者级肺部超声诊断的区域感知图聚合网络
ZAGNet: Zone-Aware Graph Aggregation Network for Patient-Level Lung Ultrasound Diagnosis
arXiv 2610.02263 · 2026-10-05光滑二元词中的洗牌平方与Kolakoski序列
Shuffle squares in smooth binary words and the Kolakoski sequence
arXiv 2610.02262 · 2026-10-05BMY线上的小Lefschetz纤维化
Small Lefschetz fibrations on the BMY line
arXiv 2610.02261 · 2026-10-05MintFlow：约束流匹配的最小轨迹干预
MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching
arXiv 2610.02260 · 2026-10-05实时机器学习推理中流滞后下的特征新鲜度预算
Feature Freshness Budgets for Real-Time ML Inference Under Stream Lag
arXiv 2610.02259 · 2026-10-05重尾噪声下的无参数区间动态遗憾
Parameter-Free Interval-Dynamic Regret under Heavy-Tailed Noise
arXiv 2610.02258 · 2026-10-05黎曼几何中的dagger范畴
Dagger Categories in Riemannian Geometry
arXiv 2610.02257 · 2026-10-05TRACE：一个使用官方运行文本进行电价预测的可复现基准
TRACE: A Reproducible Benchmark for Electricity Price Forecasting with Official Operational Text
arXiv 2610.02256 · 2026-10-05MACTS-EM：具有涌现记忆的多智能体协作时间序列预测
MACTS-EM: Multi-Agent Collaborative Time Series Forecasting with Emergent Memory
arXiv 2610.02255 · 2026-10-05利用大型语言模型克服解释结构建模的挑战
Overcoming Challenges of Interpretive Structural Modeling with Large Language Models
arXiv 2610.02254 · 2026-10-05Dropout神经网络的逼近性质：Sobolev速率与置信界
Approximation Property of Dropout Neural Networks: Sobolev Rates and Confidence Bounds
arXiv 2610.02253 · 2026-10-05科学仿真器中的反事实预测：无需受控实验
Counterfactual Predictions in Scientific Emulators Without Controlled Experiments
arXiv 2610.02252 · 2026-10-05面向扩散草稿树的排序感知投机采样
Rank-Aware Speculative Sampling for Diffusion Draft Trees
arXiv 2610.02251 · 2026-10-05克尔黑洞产生超轻轴子。第三部分：其轴子风的命运
Generation of UL-Axions by a Kerr Black Hole. Part III: The fate of its Axion Wind
arXiv 2610.02250 · 2026-10-05不同假设下基于MS/MS谱图的指纹预测的最近邻基线方法
Nearest-neighbour baselines for fingerprint prediction from MS/MS spectra under different assumptions
arXiv 2610.02249 · 2026-10-05面向地表预测中非平稳偏差的状态空间遗忘学习
State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting
arXiv 2610.02248 · 2026-10-05迈向用语言控制生物：细胞、类器官和生物机器人的提示条件干预的离线学习
Toward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots
arXiv 2610.02247 · 2026-10-05开发用于反应选择的多维、序贯sWeight程序，重点强调在CLAS12上的Kaon鉴别
Developing Multi-Dimensional, Sequential sWeighting Routines for Reaction Selection with Emphasis on Kaon Identification at CLAS12
arXiv 2610.02246 · 2026-10-05缺失的潜在变量，而非缺失的模拟器：面向真实JWST反演的半径增强推断
A Missing Latent, Not a Missing Simulator: Radius-Augmented Inference for Real JWST Retrieval
arXiv 2610.02245 · 2026-10-05流形的同伦自等价
Homotopy Self-Equivalences of Manifolds
arXiv 2610.02244 · 2026-10-05关于某些Artin群、可构造可解群、广义Baumslag-Solitar群及$SL_n(\Z)$的非交换外平方的剩余有限性
On the residual finiteness of the non-abelian exterior square of some Artin groups, constructible soluble groups, generalised Baumslag-Solitar groups and $SL_n(\Z)$
arXiv 2610.02243 · 2026-10-05RxnOptBench：用于有机方法学中反应条件优化的LLM基准测试
RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology
arXiv 2610.02242 · 2026-10-05面向万亿规模混合专家模型的硬件原生联合稀疏量化
Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts
arXiv 2610.02241 · 2026-10-05校准校验和：bfloat16 GEMM 上单侧 ABFT 的经验性误报界限及其未能捕获的内容
Calibrating the Checksum: An Empirical False-Positive Bound for One-Sided ABFT on bfloat16 GEMM, and What It Fails to Catch
arXiv 2610.02240 · 2026-10-05CORE：KV缓存的覆盖校准与驱逐质量再分配
CORE: COverage CAlibration and Evicted-Mass REdistribution for KV Cache
arXiv 2610.02235 · 2026-10-05谱交叉诊断多重量子化涡旋分裂
Spectral Crossings Diagnose Multiply Quantized Vortex Splitting
arXiv 2610.02234 · 2026-10-05利用能量引导的流匹配实现单细胞扰动响应的泛化预测
Generalizable single-cell perturbation response prediction using energy-guided flow matching
arXiv 2610.02232 · 2026-10-05
