2026-09论文中文摘要
通过医学本体与认知映射的无训练临床推理：一种符号-概率知识图谱框架
Training-Free Clinical Reasoning through Medical Ontologies and Cognitive Mapping: A Symbolic-Probabilistic Knowledge Graph Framework
arXiv 2609.35298 · 2026-09-29AbGaze：用于端到端抗体设计的注意力几何表示学习
AbGaze: Attentive Geometric Representation Learning for End-to-End Antibody Design
arXiv 2609.35296 · 2026-09-29基于仿真的推理用于板混响系统辨识
Simulation-Based Inference for Plate Reverb System Identification
arXiv 2609.35295 · 2026-09-29超越少说：面向信息丰富且忠实的视觉-语言模型的细粒度对齐
Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models
arXiv 2609.35294 · 2026-09-29决策而非生成：基于Jev类型化决策的竞争性维度ABSA
Decide, Don't Generate: Competitive Dimensional ABSA with Jev's Typed Decisions
arXiv 2609.35293 · 2026-09-29先脚手架后内化：扩散Transformer的表示注入
Scaffold Then Internalize: Representation Injection for Diffusion Transformers
arXiv 2609.35292 · 2026-09-29窄域多模态微调可诱发涌现性错位
Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment
arXiv 2609.35291 · 2026-09-29EvoIn：弥合进化与内化以实现智能体微调
EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning
arXiv 2609.35290 · 2026-09-29域自适应零样本图像增强：基于局部约束扩散引导
Domain-adaptive Zero-Shot Image Enhancement via Locality-Constrained Diffusion Guidance
arXiv 2609.35289 · 2026-09-29球状融合范畴的维数块
The dimension block of a spherical fusion category
arXiv 2609.35287 · 2026-09-29论点与信头：AI评估中的来源-立场一致性
The Argument and the Letterhead: Source-Position Coherence in AI Evaluation
arXiv 2609.35286 · 2026-09-29文本化用户品味：面向大规模基础模型推荐系统的自然语言用户上下文
Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale
arXiv 2609.35285 · 2026-09-29共线激光光谱中的拉曼跃迁用于高精度频率测量
Raman Transitions in Collinear Laser Spectroscopy for High-Precision Frequency Measurements
arXiv 2609.35284 · 2026-09-29双色强场散射重构分子离子量子态
Reconstructing Molecular-Ion Quantum States with Two-Color Strong-Field Scattering
arXiv 2609.35283 · 2026-09-29GKP-级联qLDPC码的电路级基准测试
Circuit-level benchmarks of GKP-concatenated qLDPC Codes
arXiv 2609.35282 · 2026-09-29同质面板LLM辩论中的坍缩与修正测量
Measuring Collapse and Correction in Homogeneous-Panel LLM Debate
arXiv 2609.35279 · 2026-09-29评估层级感知深度学习用于泰罗尼安音符识别
Evaluating Hierarchy-Aware Deep Learning for the Recognition of Tironian Notes
arXiv 2609.35277 · 2026-09-29非光滑随机凸-凹鞍点问题的无投影算法
Projection-Free Algorithms for Nonsmooth Stochastic Convex-Concave Saddle-Point Problems
arXiv 2609.35275 · 2026-09-29多吸引子图神经网络：超越唯一均衡的集值表达性
Multi-Attractor GNNs: Set-Valued Expressivity Beyond Unique Equilibria
arXiv 2609.35274 · 2026-09-29物理信息自监督生成数字脑部MRI体模：基于加权图像与可微分MRI模拟
Physics-informed self-supervised generation of digital brain MRI phantoms from weighted images using differentiable MRI simulation
arXiv 2609.35273 · 2026-09-29当语言胜于图像：理解视觉-语言模型中的语言偏差
When Words Speak Louder than Images: Towards Understanding Language Bias in Vision-Language Models
arXiv 2609.35272 · 2026-09-29广义LIMDD：群模决策图的简洁性与规范性
Generalized LIMDDs: Succinctness and Canonicity for Decision Diagrams Modulo a Group
arXiv 2609.35271 · 2026-09-29吸引控制的扭矩组织和摩擦颗粒物质中的旋转态
Attraction-controlled torque organization and rotational states in frictional granular matter
arXiv 2609.35270 · 2026-09-29eval-unlearn：文本到图像扩散模型中的概念遗忘基准测试
eval-unlearn: Benchmarking unlearning in Text-to-Image Diffusion Models
arXiv 2609.35269 · 2026-09-29SpikeCredit：用于稀疏奖励强化学习的时间信用载体
SpikeCredit: Temporal Credit Carrier for Reinforcement Learning with Sparse Rewards
arXiv 2609.35268 · 2026-09-29GuardPIBT：反事实门控神经引导用于超大规模三维多智能体路径规划
GuardPIBT: Counterfactually Gated Neural Guidance for Ultra-Large-Scale 3D Multi-Agent Path Finding
arXiv 2609.35267 · 2026-09-29规范自由度与Lindbladian学习的高效算法
Gauge freedom and efficient algorithms for Lindbladian learning
arXiv 2609.35265 · 2026-09-29先修复再融合：面向损坏但仍存在的传感器的冻结宿主适配
Repair Before You Fuse: Frozen-Host Adaptation for Corrupted-but-Present Sensors
arXiv 2609.35264 · 2026-09-29WavePP：前缀复用下的高吞吐流水线并行LLM预填充
WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse
arXiv 2609.35263 · 2026-09-29基于评分标准的在线策略自蒸馏用于大语言模型个性化
Rubric-Aware On-Policy Self-Distillation for LLM Personalization
arXiv 2609.35262 · 2026-09-29印记读取器：从权重更新读出到行为干预
Imprint Reader: From Weight-Update Readout to Behavioral Intervention
arXiv 2609.35261 · 2026-09-29脉冲神经网络中的延迟与精度权衡
Latency and accuracy tradeoffs in Spiking Neural Networks
arXiv 2609.35260 · 2026-09-29在线策略还是离线策略学习？蒸馏动态的系统研究
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
arXiv 2609.35259 · 2026-09-29离散统一气体动理学格式的一种保守多级自适应速度空间方法
A Conservative Multi-Level Adaptive Velocity-Space Method for the Discrete Unified Gas-Kinetic Scheme
arXiv 2609.35258 · 2026-09-29AIM-ZO：基于激活信息子空间维护的零阶大语言模型微调
AIM-ZO: Activation-Informed Subspace Maintenance for Zeroth-Order LLM Fine-Tuning
arXiv 2609.35257 · 2026-09-29迈向可靠的人工智能数据科学家：配备工作流约束的数据智能体
Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses
arXiv 2609.35255 · 2026-09-29拓扑非平凡时空中的奇异引力理论
Exotic gravity theory in topologically non-trivial spacetimes
arXiv 2609.35253 · 2026-09-29弱Hall猜想、逼近增益与连分数
Weak Hall's conjecture, approximation gains, and continued fractions
arXiv 2609.35252 · 2026-09-29绿色语言与自由逆幺半群的增长
Green languages and growth of free inverse monoids
arXiv 2609.35251 · 2026-09-29SCBO：面向基于LLM的社会调查的语义连贯批处理与排序
SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys
arXiv 2609.35250 · 2026-09-29空间嫁接：为流匹配机器人策略锚定3D特征
Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policies
arXiv 2609.35249 · 2026-09-29带符号的欧拉-史密斯剖面：分次代数
Signed Euler--Smith Profiles of Graded Algebras
arXiv 2609.35248 · 2026-09-29AnswerMap: 从答案后验中获取VLM的忠实空间可解释性
AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors
arXiv 2609.35247 · 2026-09-29硬约束概率因子图神经网络用于非高斯不确定性下的配电网状态估计
Hard-Constrained Probabilistic Factor Graph Neural Network for Distribution System State Estimation under Non-Gaussian Uncertainty
arXiv 2609.35246 · 2026-09-29联图的反魔法性
Antimagicness of join graphs
arXiv 2609.35245 · 2026-09-29水平还是垂直？管理注意力与组织结构
Horizontal or Vertical? Managerial Attention and Organizational Structure
arXiv 2609.35244 · 2026-09-29时分复用光子量子储层的精确多项式任务-风险桥接
An Exact Polynomial Task-Risk Bridge for Time-Multiplexed Photonic Quantum Reservoirs
arXiv 2609.35243 · 2026-09-29DrawingsDreamer：一种统一的多视图工程图纸生成模型
DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model
arXiv 2609.35242 · 2026-09-29超临界对偶 k-Minkowski 流与一般给定数据：先验估计与渐近收敛
Supercritical dual k-Minkowski flows with general prescribed data: a priori estimates and asymptotic convergence
arXiv 2609.35241 · 2026-09-29解构肺癌CT/LDCT人工智能：临床任务、证据链与转化差距的系统性证据图谱
Disentangling Lung-Cancer CT/LDCT AI: A Systematic Evidence Map of Clinical Tasks, Evidence Chains, and Translational Gaps
arXiv 2609.35240 · 2026-09-29
