2026-09论文中文摘要
超越表面形式：以符号编辑测试大语言模型的逻辑推理能力
Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMs
arXiv 2608.30256 · 2026-09-01CAMIE：用于Snap动态产品广告检索的协同交互感知多模态物品嵌入
CAMIE: Co-Engagement-Aware Multimodal Item Embeddings for Snap Dynamic Product Ads Retrieval
arXiv 2608.30255 · 2026-09-01带可逆边界的双弛豫时间向量格子玻尔兹曼格式的网格均匀幂稳定性
Mesh-Uniform Power Stability of Two-Relaxation-Time Vector Lattice Boltzmann Schemes with Reversible Boundaries
arXiv 2608.30253 · 2026-09-01强草稿需要紧凑记忆：带压缩KV缓存的长上下文推测解码
Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache
arXiv 2608.30252 · 2026-09-01SetMIR：将多兴趣检索视为集合预测问题
SetMIR: Multi-Interest Retrieval as Set Prediction
arXiv 2608.30251 · 2026-09-01用非推理型大语言模型从自然语言生成工作流有向无环图（DAG）
Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs
arXiv 2608.30250 · 2026-09-01不定子空间的格拉斯曼流形
The Grassmannian of indefinite subspaces
arXiv 2608.30249 · 2026-09-01DSEffi-Bench：揭示大语言模型在高效数据科学代码生成中的能力
DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation
arXiv 2608.30248 · 2026-09-01OPUS：一个简单而有效的开放词汇检测统一框架
OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection
arXiv 2608.30247 · 2026-09-01ZFC中具有非PAC一致学习器的VC维为1的Borel概念类
A Borel Concept Class of VC Dimension One with a Non-PAC Consistent Learner in ZFC
arXiv 2608.30246 · 2026-09-01相对极值投影子的ABRR求和公式
ABRR Summation Formulas for Relative Extremal Projectors
arXiv 2608.30245 · 2026-09-01有限群体LQG社会控制的分散策略：一种强化学习方法
Decentralized Strategies for Finite Population LQG Social Control: A Reinforcement Learning Approach
arXiv 2608.30244 · 2026-09-01CanonNav：跨平台视觉导航中解耦导航行为与相机几何
CanonNav: Disentangling Navigation Behavior from Camera Geometry in Cross-Platform Visual Navigation
arXiv 2608.30242 · 2026-09-01PaperBanana-Interact：基于多轮人类反馈的科学图表优化
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback
arXiv 2608.30241 · 2026-09-01基于无偏MCMC的马尔可夫链池解码的GPU并行化
GPU-Parallelization of Markov Chain Pool Decoding with Unbiased MCMC
arXiv 2608.30239 · 2026-09-01四项二元多项式乘法的无限制布尔乘法复杂度：有理点、Hasse 射流与非线性反馈的失效
Unrestricted Boolean Multiplicative Complexity of Four-Term Binary Polynomial Multiplication: Rational Places, Hasse Jets, and the Failure of Nonlinear Feedback
arXiv 2608.30238 · 2026-09-01关于Hirzebruch曲面上秩2向量丛的模空间的注记
A Note On the moduli space of rank two vector bundles on Hirzebruch surfaces
arXiv 2608.30236 · 2026-09-01结合离散结构编码与相似实体信息的基于大语言模型的知识图谱补全
LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information
arXiv 2608.30235 · 2026-09-01CoLa-ICD：一种用于长尾自动医学编码的知识增强框架
CoLa-ICD: A Knowledge-Enhanced Framework for Long-Tail Automated Medical Coding
arXiv 2608.30234 · 2026-09-01面向通用视觉 grounding 的语义-空间判别性增强
Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding
arXiv 2608.30233 · 2026-09-01分数阶薛定谔算子的强唯一延拓
Strong Unique Continuation for Fractional Schrödinger Operators
arXiv 2608.30232 · 2026-09-01神经回路中的“多即不同”：生物神经网络典型循环基序中有效理论的代数涌现
"More Is Different'' in Neural Circuits: Algebraic Emergence of Effective Theories in Canonical Recurrent Motifs of Biological Neuronal Networks
arXiv 2608.30231 · 2026-09-01量化并缓解大语言模型中的朝鲜语谚文初声、中声、终声（Jamo）层面的排版漏洞
Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models
arXiv 2608.30229 · 2026-09-01SpiderLS：利用完整ZX归约实现格手术编译
SpiderLS: Leveraging Full ZX Reduction for Lattice Surgery Compilation
arXiv 2608.30228 · 2026-09-01ELASTIC：足球中事件数据与追踪数据的基于轨迹的同步方法
ELASTIC: Trajectory-Based Synchronization of Event and Tracking Data in Soccer
arXiv 2608.30227 · 2026-09-01LaMoC：面向大语言模型的损失感知模块化压缩方法
LaMoC: Loss-Aware Modular Compression for LLMs
arXiv 2608.30226 · 2026-09-01从名义价值到实际价值重新定义稳定币：一种最大似然方法
Redefining Stablecoins from Nominal to Real Value: A Maximum Likelihood Approach
arXiv 2608.30225 · 2026-09-01差异推理路由：在电商中实现成本感知的大语言模型标注
The Differential Reasoning Router: Operationalizing Cost-Aware LLM Annotation in E-commerce
arXiv 2608.30224 · 2026-09-01基于相干风险测度的多类多组分类问题公平性研究
Fairness in multi-class multi-group classification problems via contextial coherent risk measures
arXiv 2608.30223 · 2026-09-01倾转旋翼双旋翼无人机的优化模块化设计与开发
Optimized Modular Design and Development of a Tilt-Rotor Bicopter Drone
arXiv 2608.30222 · 2026-09-01无约束协方差下的立方根高斯近似
Cubic-Root Gaussian Approximation under Unrestricted Covariance
arXiv 2608.30221 · 2026-09-01基于单平面荧光透视的无造影剂 untethered 血管内微型机器人自主导航
Contrast-Free Autonomous Navigation of Untethered Endovascular Microrobots Using Single-Plane Fluoroscopy
arXiv 2608.30220 · 2026-09-01尾部的幂律优势是否胜过全局q-高斯描述？
Does the Power-Law Advantage in the Tails Outweigh the Global q-Gaussian Description?
arXiv 2608.30219 · 2026-09-01用于可部署连续时间4D高斯重建的摊销锚点细化
Amortized Anchor Refinement for Deployable Continuous-Time 4D Gaussian Reconstruction
arXiv 2608.30218 · 2026-09-01通过纽结代数紧化曲面的$\boldsymbol{\rm SL}(3,\boldsymbol{\rm C})$特征簇
Compactification of $\operatorname{SL}(3,\mathbb{C})$-Character Varieties of Surfaces via Skein Algebras
arXiv 2608.30217 · 2026-09-01基于标签引导神经主题模型的标签语义扩展
Label Semantic Expansion via Label Guided Neural Topic Modeling
arXiv 2608.30216 · 2026-09-01采用带离子电喷推进器的立方卫星控制退役卫星与空间碎片
Control of Decommissioned Satellites and Space Debris Using CubeSats with Ion Electrospray Engines
arXiv 2608.30215 · 2026-09-01SPARK：基于大规模科学文献的骨架引导推理合成
SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature
arXiv 2608.30214 · 2026-09-01高棉语文本识别与分词联合模型研究
Towards a Joint Khmer Text Recognition and Word Segmentation
arXiv 2608.30213 · 2026-09-01前沿视觉语言模型在检测AI生成肖像方面已超过年轻人，但在校准能力上并未超越
Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibration
arXiv 2608.30210 · 2026-09-01圆柱Neumann波动模型的精确色散与Strichartz估计
Sharp Dispersive and Strichartz Estimates for the Neumann Cylindrical Wave Model
arXiv 2608.30208 · 2026-09-01面向RAN切片的智能量子深度强化学习
Agentic Quantum Deep Reinforcement Learning for RAN Slicing
arXiv 2608.30206 · 2026-09-01基于扩散模型的千米级概率临近降水预报精细化方法
Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting
arXiv 2608.30205 · 2026-09-01当模型“听到”它们所期待的：诊断多模态讽刺检测中的韵律启发式算法
When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection
arXiv 2608.30204 · 2026-09-01竞争-单射分配：支持列表结构与最大锚点EFX₀证书
Rival-Injective Allocations: Support-List Structure and Maximum-Anchor EFX$_0$ Certificates
arXiv 2608.30203 · 2026-09-01ReLViC：采用分散分组与可控分组依赖的抗损失学习视频编码
ReLViC: Loss-Resilient Learned Video Coding with Dispersed Packetization and Controllable Packet Dependencies
arXiv 2608.30202 · 2026-09-01通过提升谱面体包含性实现Wasserstein分布鲁棒小信号稳定约束的交流最优潮流的预测误差空间中的可证安全半径
Certified Safety Radii in Forecast-Error Space for Wasserstein Distributionally Robust Small Signal Stability-Constrained AC Optimal Power Flow via Lifted Spectrahedral Containment
arXiv 2608.30201 · 2026-09-01基于LAMOST第十次数据释放（DR10）识别的OB型恒星
OB stars identified in LAMOST Data Release 10
arXiv 2608.30200 · 2026-09-01用于寒区配电网影响分析的高分辨率合成电动汽车充电数据集：挪威特隆赫姆（2020-2030）
A High-Resolution Synthetic EV Charging Dataset for Cold-Climate Distribution Grid Impact Analysis: Trondheim, Norway (2020-2030)
arXiv 2608.30199 · 2026-09-01当错误成为记忆：多轮记忆增强大型语言模型中的因果路径追踪
When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs
arXiv 2608.30198 · 2026-09-01
