2026-09论文中文摘要
自适应共形再分配用于医学图像分类中的类间过渡不确定性
Adaptive Conformal Redistribution for Inter-class Transitional Uncertainty in Medical Image Classification
arXiv 2609.13303 · 2026-09-15AI使用条件与伦理决策中的视角多样性：人类推理过程的初步研究
AI Use Conditions and Perspective Diversity in Ethical Decision-Making: A Pilot Study of Human Reasoning Processes
arXiv 2609.13302 · 2026-09-15大型语言模型驱动的人工智能时代的天体物理学
Astrophysics in the Era of Artificial Intelligence powered by Large Language Models
arXiv 2609.13301 · 2026-09-15Poisson 铅笔、Lie 对称性与耦合非线性波系统的 Hamilton 约化：切 KdV 几何与椭圆模量
Poisson Pencils, Lie Symmetries and Hamiltonian Reductions of a Coupled Nonlinear Wave System:Tangent KdV Geometry and Elliptic Moduli
arXiv 2609.13300 · 2026-09-15从实验到决策：在自主编码研究中重用证据
From Experiments to Decisions: Reusing Evidence in Autonomous Coding Research
arXiv 2609.13299 · 2026-09-15变分模板匹配与统计融合用于图案化结构中的异常检测
Variational Template Matching with Statistical Fusion for Anomaly Detection in Patterned Structures
arXiv 2609.13298 · 2026-09-15关于 $\Pi^0_1$-免疫性的低度性注记
A Note on Lowness for $Π^0_1$-Immunity
arXiv 2609.13297 · 2026-09-15利用图像-问题依赖性改进VLM测试时强化学习
Harnessing Image Question Dependence for Better VLM Test-time Reinforcement Learning
arXiv 2609.13296 · 2026-09-15遍历控制与受控扩散在机器人学习中的应用：综述与教程
Ergodic Control and Controlled Diffusion for Robot Learning: Review and Tutorial
arXiv 2609.13295 · 2026-09-15可靠的自我中心动作预测：通过时间可靠性抑制与组合图解码
Reliable Egocentric Action Anticipation via Temporal Reliability Suppression and Compositional Graph Decoding
arXiv 2609.13293 · 2026-09-15Aries：面向能源行业的专有中期天气预报模型
Aries: A Proprietary Medium-Range Weather Prediction Model for the Energy Industry
arXiv 2609.13292 · 2026-09-15ScorePrompts：通过分析对符号音乐乐谱进行自然语言探索
ScorePrompts: Natural-Language Exploration of Symbolic Music Scores through Analysis
arXiv 2609.13291 · 2026-09-15通过惠更斯耦合摆动力学突破四足机器人的速度缩放限制
Breaking speed scaling in quadrupedal robots via Huygens' coupled-pendulum dynamics
arXiv 2609.13290 · 2026-09-15通过精细化执行器建模与自适应指令调度扩展四足机器人运动速度极限
Extending the Speed Limit of Quadrupedal Locomotion via Refined Actuator Modeling and Adaptive Command Scheduling
arXiv 2609.13289 · 2026-09-15面向视频问答的目标校验可靠性分数精化
Target-Checked Reliability Score Refinement for Video Question Answering
arXiv 2609.13288 · 2026-09-15LLaDA-UI：将块级扩散引入视觉语言GUI智能体
LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents
arXiv 2609.13287 · 2026-09-15马登-朱利安振荡的尺度分析
Scale analysis for the Madden$-$Julian oscillation
arXiv 2609.13286 · 2026-09-15双值超一致注释逻辑中的证据源解耦：一种用于教育评估的广义PAL2v框架
Decoupling Evidence Sources in Paraconsistent Logic: A Generalized PAL2v Framework for Educational Assessment
arXiv 2609.13284 · 2026-09-15月球遥感的多模态-多分辨率基础模型
Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing
arXiv 2609.13283 · 2026-09-15GaugeDefect：通过特征传输曲率检测表面异常
GaugeDefect: Detecting Surface Anomalies by Curvature of Feature Transport
arXiv 2609.13282 · 2026-09-15RxScribe Bench：用于评估视觉语言模型在印度门诊处方上的多轴基准
RxScribe Bench: A Multi-Axis Benchmark for Evaluating Vision-Language Models on Indian Outpatient Prescriptions
arXiv 2609.13280 · 2026-09-15基于张量的混沌感知
Tensor-Based Chaotic Perception
arXiv 2609.13278 · 2026-09-15SomBench：推进月球科学机器学习的基准数据集
SomBench: Benchmark Dataset for Advancing Machine Learning in Lunar Science
arXiv 2609.13277 · 2026-09-15E-ALS：面向近似逻辑综合的近似潜力感知E图重写
E-ALS: Approximation-Potential-Aware E-Graph Rewriting for Approximate Logic Synthesis
arXiv 2609.13276 · 2026-09-15地球系统模型参数优化的物理-机器学习多保真度策略：准地转概念验证
A Physics--ML Multi-Fidelity Strategy for Earth System Model Parameter Optimization: A QG Proof-of-Concept
arXiv 2609.13275 · 2026-09-15弃权错误与CUAD中的片段支持：一个可审计的合同抽取案例研究
Abstention Errors and Segment Support in CUAD: An Auditable Contract-Extraction Case Study
arXiv 2609.13274 · 2026-09-15强非局部连续介质的热力学框架
A thermomechanical framework for strongly nonlocal continua
arXiv 2609.13273 · 2026-09-15引力波信号去噪的新型深度学习架构综述
Survey of Novel Deep Learning Architectures for Denoising Gravitational-wave Signals
arXiv 2609.13272 · 2026-09-15CANAL：医学图像分割中差分隐私特征蒸馏的信道感知噪声分配
CANAL: Channel-Aware Noise Allocation for Differentially Private Feature Distillation in Medical Image Segmentation
arXiv 2609.13271 · 2026-09-15多无人机分布式模型预测控制中的冲突预测可变时域
Conflict-Predictive Variable Horizons in Multi-Drone Distributed Model Predictive Control
arXiv 2609.13270 · 2026-09-15通过投影卷绕序的帧同步手势检测
Frame-Synchronous Hand Gesture Detection by Projected Winding Order
arXiv 2609.13269 · 2026-09-15能力路由的视觉检索与证据串联用于长上下文文档问答
Capability-Routed Visual Retrieval and Evidence Threading for Long-Context Document Question Answering
arXiv 2609.13268 · 2026-09-15科学图表理解的结构-标记证据锚定推理
Structure-Token Evidence-Anchored Reasoning for Scientific Chart Understanding
arXiv 2609.13267 · 2026-09-15黑洞、引力波与时空奇点——勒梅特会议2024
Black Holes, Gravitational Waves and Space-Time Singularities Lemaitre Conference 2024
arXiv 2609.13266 · 2026-09-15前视近红外对农机可通行性的颜色信息增益甚微：传感器相关空间泄漏的站点分离评估
Forward-Facing Near-Infrared Adds Little to Colour for Farm-Machinery Traversability: A Site-Disjoint Evaluation of Sensor-Dependent Spatial Leakage
arXiv 2609.13265 · 2026-09-15BEACON：面向主体特定视频生成的行为与外观控制
BEACON: Behavior and Appearance Control for Subject-Specific Video Generation
arXiv 2609.13264 · 2026-09-15多视图运动恢复结构实现三维有向射影形状分析
Multi-View Structure-from-Motion Enables Oriented Projective Shape Analysis in Three Dimensions
arXiv 2609.13263 · 2026-09-15填补未见区域：基于3D高斯泼溅的场景外推
Filling the Unseen: Scene Extrapolation via 3D Gaussian Splatting
arXiv 2609.13262 · 2026-09-15从过程损失到组装增益：多智能体LLM协作的人类基础诊断
From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration
arXiv 2609.13261 · 2026-09-15从掩蔽到合并：重新思考SpecAugment以实现高效的音频频谱图Transformer
From Masking to Merging: Rethinking SpecAugment for Efficient Audio Spectrogram Transformer
arXiv 2609.13260 · 2026-09-15TryOnReward：学习用于虚拟试穿强化微调的中央凹一致性
TryOnReward: Learning Foveated Consistency for Reinforcement Fine-Tuning of Virtual Try-On
arXiv 2609.13259 · 2026-09-15可解释的时间视频推理：EventGraph 与 EventField
Interpretable Temporal Video Reasoning with EventGraph and EventField
arXiv 2609.13258 · 2026-09-15采样余量并非选择增益：视频世界模型测试时扩展的计算价值审计
Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models
arXiv 2609.13257 · 2026-09-15局域化景观作为异质系统的算子诱导几何
Localization Landscapes as Operator-Induced Geometry for Heterogeneous Systems
arXiv 2609.13256 · 2026-09-15多模态面部状态分析综合综述：任务、方法与资源
A Comprehensive Review of Multimodal Facial State Analysis: Tasks, Methods, and Resources
arXiv 2609.13255 · 2026-09-15（如何）多模态大语言模型像人类一样报告双稳态图像？
(How) Do MLLMs Report Bistable Images Like Humans?
arXiv 2609.13254 · 2026-09-15一种具有均值场环境反馈的多智能体Q学习的进化计算框架
An Evolutionary Computation Framework for Multi-Agent Q-Learning with Mean-Field Environmental Feedback
arXiv 2609.13253 · 2026-09-15深度学习预测恒星条件下等离子体的不透明度
Opacity predictions in plasmas under stellar conditions using deep learning
arXiv 2609.13252 · 2026-09-15保持图像外扩中主体清晰度的多尺度小波监督
Preserving Subject-Clarity in Image Outpainting with Multiscale Wavelet Supervision
arXiv 2609.13251 · 2026-09-15多模态大语言模型无关的即插即用关键帧选择方法用于长视频理解的评估
Evaluation of MLLM-Agnostic Plug-and-Play Keyframe Selection Methods for Long Video Understanding
arXiv 2609.13250 · 2026-09-15
