2026-09论文中文摘要
结合序列标注与方面代码切换增强的生成模型改进跨语言方面级情感分析
Generative Models Enhanced by Sequence Labelling and Aspect-Code Switching Improve Cross-lingual Aspect-Based Sentiment Analysis
arXiv 2608.30425 · 2026-09-01面向认知过程感知的主动式写作支持
Towards Cognitive Process-Aware Proactive Writing Support
arXiv 2608.30424 · 2026-09-01ObjectSplat：通过物体层级网格溅射提升3D场景的网格保真度与交互性
ObjectSplat: Improving Mesh Fidelity and Interactivity for 3D Scenes via Object-Level Mesh Splatting
arXiv 2608.30423 · 2026-09-01重新审视迭代集合概念
The Iterative Conception Reconsidered
arXiv 2608.30422 · 2026-09-01无穷小不可逆过程的d'Q = TdS：论克劳修斯不等式的微分形式
d'Q = TdS for Infinitesimal Irreversible Processes: On the Differential Form of the Clausius Inequality
arXiv 2608.30421 · 2026-09-01现实小样本标注协议下的 whole-slide 图像分析
Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
arXiv 2608.30420 · 2026-09-01静息态fMRI连接组预测的SPD矩阵学习外部泛化基准测试
Benchmarking External Generalization of SPD Matrix Learning for Resting-State fMRI Connectome Prediction
arXiv 2608.30418 · 2026-09-01不存在覆盖所有等变注意力的等变架构
No Equivariant Architecture Covers All Equivariant Attention
arXiv 2608.30417 · 2026-09-01手征凝聚累积量的偏差校正机器学习估计：一项回顾性格点量子色动力学案例研究
Bias-Corrected Machine-Learning Estimation of Chiral Condensate Cumulants: A Retrospective Lattice QCD Case Study
arXiv 2608.30416 · 2026-09-01广义复射影乘积空间
On generalized complex projective product spaces
arXiv 2608.30415 · 2026-09-01平面三体问题：理论预测与模拟结果
Planar Three-Body Problem: theoretical predictions and simulation results
arXiv 2608.30414 · 2026-09-01DERELAB：用生成式基准测试探究大型语言模型中的可废止推理与确认偏差
DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark
arXiv 2608.30413 · 2026-09-01随机试验中含二分类中介变量的因果中介分析的效力与样本量计算
Power and sample size calculations for causal mediation analysis with a binary mediator in randomized trials
arXiv 2608.30412 · 2026-09-01采用主动追踪点扫描光学相干断层扫描的空间或时间分辨基于相位的光视网膜成像技术
Spatially or temporally resolved phase-based optoretinography with actively-tracked point-scanning optical coherence tomography
arXiv 2608.30411 · 2026-09-01SePArate：利用弱监督从晶圆制造缺陷中分割图案
SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision
arXiv 2608.30410 · 2026-09-01群代数中斜对称元的李幂零指数
Lie nilpotency index of skew symmetric elements in group algebras
arXiv 2608.30408 · 2026-09-01由单圈图构造的边码
Edge codes constructed from unicyclic graphs
arXiv 2608.30407 · 2026-09-01局部引导的演员-评论家：利用感知子目标的评论家训练目标条件演员
Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic
arXiv 2608.30406 · 2026-09-01密集临床对比可增强大型语言模型中的医学知识更新
Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models
arXiv 2608.30405 · 2026-09-01ImageCAS-X：用于冠状动脉CT血管造影中冠状动脉分割与中心线提取的数据集和基准
ImageCAS-X: a dataset and benchmark for coronary artery segmentation and centerline extraction in coronary CT angiography
arXiv 2608.30404 · 2026-09-01为何LLM后门防御呈现碎片化？基于稀疏自编码器的特征级解释
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
arXiv 2608.30403 · 2026-09-01拓展用于光伏领域的pnictide化学空间
Extending the Pnictide Chemical Space for Photovoltaics
arXiv 2608.30402 · 2026-09-01面向体内磁共振的有效介质理论：表征可容许的磁化动力学
Towards an effective medium theory for in-vivo Magnetic Resonance: Characterizing Admissible Magnetization Dynamics
arXiv 2608.30401 · 2026-09-01面向高动态范围目标检测的实时场景自适应色调映射
Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection
arXiv 2608.30400 · 2026-09-01SemPOI-RL：对齐大语言模型语义推理以实现可解释的异地兴趣点序列生成
SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation
arXiv 2608.30399 · 2026-09-01超越极化：点式重排序中思维链的生成约束
Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking
arXiv 2608.30398 · 2026-09-01针对不可验证生成的演员条件评论家的协同进化
Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation
arXiv 2608.30397 · 2026-09-01将基础模型搭建为物理世界智能体以推动长时程导航前沿
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
arXiv 2608.30396 · 2026-09-01当大语言模型遇到树搜索：大语言模型中作为搜索的推理的系统视角
When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models
arXiv 2608.30395 · 2026-09-01TopGQ：利用拓扑信息的快速GNN后训练量化
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
arXiv 2608.30394 · 2026-09-01基础模型与农业：预训练之外的挑战
Foundation Models Meet Agriculture: Challenges Beyond Pretraining
arXiv 2608.30392 · 2026-09-01用扎根理论进行大规模智能体行为分析
Using Grounded Theory for Agent Behavior Analysis at Scale
arXiv 2608.30391 · 2026-09-01视觉医学基础模型的不确定性
Uncertainty of Vision Medical Foundation Models
arXiv 2608.30390 · 2026-09-01二次整数环上的13个未知元与卢卡斯同余式
$13$ unknowns over quadratic integer rings and Lucas congruences
arXiv 2608.30389 · 2026-09-01PRISM：基于语义隐分解的预测重组用于视角不变视频表示学习
PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Video Representation Learning
arXiv 2608.30388 · 2026-09-01多智能体AI系统中的输出证明与委托谱系
Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems
arXiv 2608.30387 · 2026-09-01DASC：面向混合线性注意力服务的感知衰减状态压缩
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
arXiv 2608.30386 · 2026-09-01通过构造中间查询结果的等价表示来检测数据库管理系统（DBMS）漏洞
Detecting DBMS Bugs by Constructing Equivalent Representations of Intermediate Query Results
arXiv 2608.30385 · 2026-09-01RSLM：用于近似最近邻搜索的无训练向量量化方法
RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
arXiv 2608.30384 · 2026-09-01使用Hyper-V套接字从恶意软件分析沙箱中进行实时数据提取
Using Hyper-V Sockets for Real-time Data Extraction from a Malware Analysis Sandbox
arXiv 2608.30383 · 2026-09-01超参数完全可控的RMSprop优化器的收敛速率
Convergence rates for the RMSprop optimizer with full control of the hyperparameters
arXiv 2608.30382 · 2026-09-01电荷有序的赝自旋动力学
Pseudospin Dynamics of Charge Order
arXiv 2608.30381 · 2026-09-01KORD：通过协议-硬件协同设计突破无经销商FSS的密钥生成瓶颈
KORD: Breaking the Key-Generation Bottleneck in Dealerless FSS via Protocol--Hardware Co-Design
arXiv 2608.30379 · 2026-09-01致密活性悬浮液中各向异性示踪剂的最优输运
Optimal Transport of an Anisotropic Tracer in Dense Active Suspensions
arXiv 2608.30377 · 2026-09-01Kathleen记忆：无注意力的长度不变一次性回忆
Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention
arXiv 2608.30376 · 2026-09-01基于量子计算的碎裂函数第一性原理预测
First-principle predictions of fragmentation functions via quantum computing
arXiv 2608.30375 · 2026-09-01零空间SVD估计的紧致无穷阶误差分析
Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation
arXiv 2608.30374 · 2026-09-01超越共识：用于主观评估的多智能体大语言模型评判器中的向下偏差与角色不对称
Beyond Consensus: Downward Bias and Role Asymmetry in Multi-Agent LLM Judges for Subjective Evaluation
arXiv 2608.30373 · 2026-09-01基于概率景观的MCQA基准测试审计
Auditing MCQA Benchmarks through Probability Landscapes
arXiv 2608.30372 · 2026-09-01正则二分酉轨道上的边缘谱分布
Marginal spectral distributions on regular bipartite unitary orbits
arXiv 2608.30370 · 2026-09-01
