2026-07论文中文摘要
分布优先的总体模拟：非怪异大语言模型角色建模中的崩溃、校准和召回
Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling
arXiv 2607.18310 · 2026-07-22使用具有外部控制的增强图神经常微分方程对非定常翼型空气动力学进行时空预测
Spatio-Temporal Prediction of Unsteady Airfoil Aerodynamics Using Augmented Graph Neural Ordinary Differential Equations with Exogenous Controls
arXiv 2607.18309 · 2026-07-22灰箱仿真模型的智能校准：一种由大语言模型驱动的替代方法
Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative
arXiv 2607.18308 · 2026-07-22类空动量转移平方有限值下质子电形状因子的零点
Zero of the proton electric form factor in the finite value of the spacelike momentum transfer squared
arXiv 2607.18307 · 2026-07-22用于锐度感知最小化的梯度能量引导的逐块扰动
Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization
arXiv 2607.18306 · 2026-07-22信息阴影：衡量语言模型学习的结构限制
The Information Shadow: Measuring Structural Limits on What Language Models Can Learn
arXiv 2607.18305 · 2026-07-22TD-DPO：用于减轻临床自闭症干预对话中谄媚行为的差异感知偏好优化
TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue
arXiv 2607.18304 · 2026-07-22语言模型的更好开端：领域条件位置偏移
A Better Start for Language Models: Domain-Conditional Position Offsets
arXiv 2607.18302 · 2026-07-22超越贝叶斯主义和完全信息的激励探索
On Incentivized Exploration beyond Bayesianism and Full-Information
arXiv 2607.18300 · 2026-07-22使用带控制的动态模式分解在单个气候实现中分离强迫和内部气候变率
Disentangling Forced and Internal Climate Variability in Single Realizations using Dynamic Mode Decomposition with Control
arXiv 2607.18298 · 2026-07-22倒谐振子相空间动力学的观测
Observation of Phase Space Dynamics of Inverted Harmonic Oscillator
arXiv 2607.18297 · 2026-07-22深度强化学习掌握Baghchal的非对称策略
Deep Reinforcement Learning to Master the Asymmetric Strategy of Baghchal
arXiv 2607.18296 · 2026-07-22人工智能驱动的碰撞模拟代理的不确定性量化：基于开源保险杠梁基准的蒙特卡洛随机失活和深度集成的比较研究
Uncertainty Quantification for AI-Driven Crash Simulation Surrogates: A Comparative Study of Monte Carlo Dropout and Deep Ensemble on Open-Source Bumper Beam Benchmark
arXiv 2607.18294 · 2026-07-22一个学生，多个教师：通过软提示特权上下文进行多任务在线策略蒸馏
One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context
arXiv 2607.18293 · 2026-07-22用于高效时变可靠性分析的双域融合长短期记忆模型
Dual-domain fused LSTM modeling for efficient time-dependent reliability analysis
arXiv 2607.18291 · 2026-07-22迈向有原则的持续异常检测：一个系统框架和基准场景
Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios
arXiv 2607.18289 · 2026-07-22用于边缘云网络联合优化的多时间尺度潜行动作深度强化学习
Multi-Timescale Latent-Action DRL for Joint Optimization in Edge-Cloud Networks
arXiv 2607.18288 · 2026-07-22BearingNAS：使用笔记本电脑获取用于轴承的传感器内智能故障诊断系统
BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop
arXiv 2607.18287 · 2026-07-22用于运行时可调公交信号优先的偏好条件多目标强化学习
Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority
arXiv 2607.18286 · 2026-07-22用于端到端射频频谱监测的边缘高效变压器
Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring
arXiv 2607.18285 · 2026-07-22压缩关键内容：神经元重要性与数据感知低秩近似用于语言模型压缩
Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression
arXiv 2607.18284 · 2026-07-22FedCC：用于胎儿超声图像中胼胝体稳健定位的基础模型低资源联邦适应
FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images
arXiv 2607.18283 · 2026-07-22ALAS：用于灵活贝叶斯优化的可加学习α-稳定核
ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian Optimization
arXiv 2607.18282 · 2026-07-22超越单维压缩：大语言模型的复合稀疏前沿
Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models
arXiv 2607.18280 · 2026-07-22超越输出空间校准：用于时间序列分类中选择性可靠性估计的频谱证据捆绑
Beyond Output-Space Calibration: Spectral Evidence Bundling for Selective Reliability Estimation in Time-Series Classification
arXiv 2607.18279 · 2026-07-22FALCON-Discover：发现校准的集中错误置信区域
FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration
arXiv 2607.18278 · 2026-07-22风险介导的传播动力学决定超越物理流动性的疫情轨迹
Risk-mediated transmission dynamics govern epidemic trajectories beyond physical mobility
arXiv 2607.18277 · 2026-07-22提高打击“力量”：重新审视初始打击速度和有效质量的作用
Improving Punching "Power": Reconsidering the roles of initial strike velocity and effective mass
arXiv 2607.18276 · 2026-07-22一种辨别演算：决策相关洞察、序列价值与遗忘作为高阶学习
A Calculus of Discernment: Decision-Relevant Insight, Sequence Value, and Forgetting as Higher-Order Learning
arXiv 2607.18275 · 2026-07-22警察与强盗问题的领域设计
Domain Design for the Cops and Robbers Problem
arXiv 2607.18274 · 2026-07-22物联网中使用轻量级支持向量回归的CoAP预测性重传超时
Predictive RTO for CoAP using Lightweight Support Vector Regression in Internet of Things
arXiv 2607.18273 · 2026-07-22本地电力市场中 prosumer 的市场策略评估
Market Strategy Evaluation for Prosumers in Local Electricity Markets
arXiv 2607.18272 · 2026-07-22使用大语言模型从时间序列中生成可解释的、数据驱动的见解
Using LLMs for Explainable, Data-Driven Insight Generation from Time Series
arXiv 2607.18271 · 2026-07-22Fence：用于大语言模型应用的专用小型语言模型护栏
Fence: Specialized SLM Guardrails for LLM Applications
arXiv 2607.18268 · 2026-07-22自主性经济学：适用于可保险的人工智能驱动的6G系统的实时风险索引
The Economics of Autonomy: Real-Time Risk Indexing for Insurable AI-Driven 6G Systems
arXiv 2607.18267 · 2026-07-22用于小型语言模型算术微调的结构化合成推理数据
Structured Synthetic Reasoning Data for Arithmetic Fine-Tuning of Small Language Models
arXiv 2607.18266 · 2026-07-22双智能体语言模型中继中的状态压缩：约束保留的封闭世界研究
State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation
arXiv 2607.18265 · 2026-07-22MUX：通过复用令牌进行连续推理
MUX: Continuous Reasoning via Multiplexed Tokens
arXiv 2607.18264 · 2026-07-22当JSON不足够时：模式约束的大语言模型排序代理的语义可靠性
When JSON Is Not Enough: Semantic Reliability of Schema-Constrained LLM Ordering Agents
arXiv 2607.18261 · 2026-07-22FindStatBench：在组合代码合成上评估大语言模型
FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis
arXiv 2607.18260 · 2026-07-22用于可信大语言模型推理的概率概念感知引导
Probabilistic Concept-Aware Steering for Trustworthy LLM Inference
arXiv 2607.18259 · 2026-07-22S2T-RLHF：基于稳定偏好的强化学习从人类反馈中的分层信用分配
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
arXiv 2607.18258 · 2026-07-22PEARL：基于自然语言的循环求解器交互式优化建模
PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language
arXiv 2607.18256 · 2026-07-22无需重新训练的跨方言泛化：MLIR 的模式派生约束解码基准测试与评估
Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR
arXiv 2607.18254 · 2026-07-22超越准确性和成本：针对动态工作负载的延迟感知大语言模型查询路由
Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads
arXiv 2607.18253 · 2026-07-22MILP-Evo：混合整数线性规划求解器的闭环全自动设计
MILP-Evo: Closed-Loop Fully Automatic Design of MILP Solvers
arXiv 2607.18252 · 2026-07-22通过分布式反馈控制实现无人机运动角度稳定中的积分 - 微分方程
Integro-differential equations in angular stabilization of drone motion by distributed feedback control
arXiv 2607.18251 · 2026-07-22儿童与基于大语言模型的聊天机器人互动中的拟人化：驱动因素和结果的系统综述
Anthropomorphism in Children's Interactions with LLM Chatbots: A Systematic Review of Drivers and Outcomes
arXiv 2607.18250 · 2026-07-22MechAInistic：一种由大语言模型引导的多智能体系统，用于基于基因组规模的约束代谢模型进行推理
MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models
arXiv 2607.18249 · 2026-07-22社交媒体干预对机器人和人类传播健康错误信息的威慑作用
Deterrence Effects of Social Media Interventions on Health Misinformation Dissemination by Bots and Humans
arXiv 2607.18248 · 2026-07-22
