2026-08论文中文摘要
SyPS：衡量大语言模型中的谄媚提示敏感性
SyPS: Measuring Sycophancy Prompt Sensitivity in Large Language Models
arXiv 2608.23837 · 2026-08-26从CT阅片时的三维注视模式预测放射科医生的专业水平
Predicting Radiologist Expertise from 3D Gaze Patterns During CT Interpretation
arXiv 2608.23836 · 2026-08-26基于图的可解释解释生成干预假设：G2I，一个两阶段贪心框架
Generating Intervention Hypotheses using Explainable Explanations on Graphs: G2I, a Two-Stage Greedy Framework
arXiv 2608.23835 · 2026-08-26Minima-KV：采用混合格式分页注意力的保留保留KV缓存压缩技术
Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention
arXiv 2608.23834 · 2026-08-26WSe₂-NiPS₃磁性范德瓦尔斯异质结构中的光谱可调控自旋极化光电流
Spectrally Programmable Spin-Polarized Photocurrents in WSe$_2$-NiPS$_3$ Magnetic van der Waals Heterostructures
arXiv 2608.23832 · 2026-08-26缓解多指令遵循强化学习中的探索偏差
Mitigating Exploration Bias in RL for Multi-Instruction Following
arXiv 2608.23830 · 2026-08-26与弹性复形相关的向量值上链/链复形
A Vector-Valued Co-Chain/Chain Complex Associated to the Elasticity Complex
arXiv 2608.23829 · 2026-08-26别放弃我：探索无人维护的亲密伴侣暴力支持应用程序的现状
Stop Abandoning Me: Exploring the Landscape of Unmaintained Intimate Partner Abuse Support Applications
arXiv 2608.23826 · 2026-08-26针对排序数据的本特（Benter）模型的高效贝叶斯推断
Efficient Bayesian Inference for Benter Models on Ranked Data
arXiv 2608.23825 · 2026-08-26位置、切片与调度： tethered毫米波无人机gNB的分层O-RAN控制
Place, Slice and Schedule: Hierarchical O-RAN Control of a Tethered mmWave UAV-gNB
arXiv 2608.23824 · 2026-08-26La₃Ni₂O₇中交织的自旋-电荷条纹序与极性晶格畸变
Intertwined spin-charge stripe order and polar lattice distortion in La$_{3}$Ni$_{2}$O$_{7}$
arXiv 2608.23823 · 2026-08-26重访PWDG-UWVF等价性
The PWDG-UWVF Equivalence Revisited
arXiv 2608.23822 · 2026-08-26Finch：化学化合物及混合物的毒性剂量反应曲线预测
Finch: Toxicity Dose Response Curve Prediction of Chemical Compounds and Mixtures
arXiv 2608.23821 · 2026-08-26从匿名形状到命名地点：一种用于触觉地图的盲文与地点语义标注工具
From Anonymous Shapes to Named Places: A Tool for Braille and Place-Semantic Annotation of Tactile Maps
arXiv 2608.23820 · 2026-08-26超越静态与线性：哪种注意力约束最符合人类阅读时间规律？
Beyond Static and Linear: What Attention Constraints Best Fit Human Reading Times?
arXiv 2608.23818 · 2026-08-26用于可解释人工智能中鲁棒性与保真度审计的形式化方法论框架：从应用到信任认证
A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification
arXiv 2608.23817 · 2026-08-26AQLoRA：一种用于快速量化LoRA微调的零搜索方案
AQLoRA: A Zero-Search Recipe for Fast Quantized LoRA Fine-Tuning
arXiv 2608.23816 · 2026-08-26应变或阴离子交换能否使不稳定结构稳定？锂硫卤化物反钙钛矿（Li$_{3}$$BA$）及其阴离子交换变体（Li$_{3}$$AB$）的能量学、晶格动力学与应变可调带隙
Can Strain or Anion Interchange Make an Unstable Structure Stable? Energetics, Lattice Dynamics and Strain-Tunable Band Gaps of Lithium Chalcohalide Antiperovskites (Li$_{3}$$BA$) and their Anion Interchange Variants (Li$_{3}$$AB$)
arXiv 2608.23815 · 2026-08-26高效评分学习：面向低成本大语言模型作文评分的多臂老虎机驱动提示选择框架
Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring
arXiv 2608.23814 · 2026-08-26数据同化：解决虚假相关性与可扩展性问题
Data Assimilation: Addressing Spurious Correlations and Scalability Issues
arXiv 2608.23813 · 2026-08-26从偏好到原则：基于评分规则的接地知识答案对齐
From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers
arXiv 2608.23812 · 2026-08-26用强化学习增强的智能体搜索生成生物医学事实核查报告
Generating Biomedical Fact-Checking Reports with RL-Enhanced Agentic Search
arXiv 2608.23811 · 2026-08-26利用几何不变稀疏自编码器发现大语言模型中的跨语言推理不变性
Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders
arXiv 2608.23809 · 2026-08-26部署掩码扩散大语言模型：基于真实硬件的特性分析与设计原则
Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware
arXiv 2608.23807 · 2026-08-26Giga-Embeddings：用于高吞吐量文本嵌入的混合专家编码器
Giga-Embeddings: Mixture-of-Experts Encoders for High-Throughput Text Embeddings
arXiv 2608.23806 · 2026-08-26内存主权推理：超越完全驻留的输出精确执行
Memory-Sovereign Inference: Output-Exact Execution Beyond Full Residency
arXiv 2608.23805 · 2026-08-26挠率与正合性
Torsion and exactness
arXiv 2608.23804 · 2026-08-26用于贝叶斯趋势滤波的图依赖收缩先验
Graph-dependent shrinkage priors for Bayesian trend filtering
arXiv 2608.23802 · 2026-08-26单位圆上特征化子群的复杂度与可Polish化性
Complexity and Polishability of characterized subgroups on the unit circle
arXiv 2608.23801 · 2026-08-26统计模型能否捕捉Mamdani的成功？社会选择、排序复选投票与模型拟合，及其在2025年纽约市民主党初选中的应用
Can statistical models capture Mamdani's success? Social choice, ranked-choice voting, and model fit, with an application to the 2025 New York City Democratic Primary
arXiv 2608.23800 · 2026-08-26无遗忘恢复：跨图像退化的持续学习
Restoring Without Forgetting: Continual Learning Across Image Degradations
arXiv 2608.23799 · 2026-08-26稳定亚当斯猜想
The Stable Adams Conjecture
arXiv 2608.23797 · 2026-08-26加速居民太阳能发电系统的普及：基于动态结构模型的政策分析
Accelerating the Adoption of Residential Solar Power Systems: Policy Analysis using a Dynamic Structural Model
arXiv 2608.23796 · 2026-08-26暗物质亚晕的新探针：基于TESS的恒星像差
A New Probe of Dark Matter Subhalos: Stellar Aberration with TESS
arXiv 2608.23795 · 2026-08-26通道专家混合：用于逐点投影的具有输入自适应混合的静态稀疏支持
Mixture of Channel Experts: Static Sparse Supports with Input-Adaptive Mixing for Pointwise Projections
arXiv 2608.23794 · 2026-08-26近似广义距离协方差的原分布
Approximating the null distribution of generalized distance covariance
arXiv 2608.23793 · 2026-08-26在 $\boldsymbol{\bigl(u,\boldsymbol{\bigr)}}$ 上把五十个双对数自变量坍缩为五项
Collapsing Fifty Dilogarithm Arguments to Five Terms over $\mathbb{Q}\bigl(u,\sqrt{4-3u^{2}}\bigr)$
arXiv 2608.23792 · 2026-08-26EmoTra-TTS：用于语音合成的流畅句内情感转换
EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis
arXiv 2608.23791 · 2026-08-26灵长类视觉揭示了鲁棒动态人工智能缺失的原理
Primate vision reveals a missing principle for robust dynamic AI
arXiv 2608.23790 · 2026-08-26轴子现象学专题：宇宙弦与超辐射的案例
Topics in the phenomenology of axions: the cases of cosmic strings and superradiance
arXiv 2608.23789 · 2026-08-26量子色动力学（QCD）中质子的光子与胶子引力形状因子
Photon and gluon gravitational form factors of proton in QCD
arXiv 2608.23788 · 2026-08-26针对TLS 1.3密码依赖项的CRQC+AI漏洞谱的基于场景的评估
A Scenario-Based Evaluation of CRQC+AI Vulnerability Spectrum for TLS 1.3 Cryptographic Dependencies
arXiv 2608.23785 · 2026-08-26通过Fedosov形变量子化构造热核与共形反常的简易方法
A simple construction of Heat Kernels and conformal anomalies via Fedosov deformation quantization
arXiv 2608.23784 · 2026-08-26面向开放文本多维度评估的维度间依赖关系
Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text
arXiv 2608.23783 · 2026-08-26GAP-Prompt：用于高效持续学习的门控自适应提示
GAP-Prompt: Gated Adaptive Prompting for Efficient Continual Learning
arXiv 2608.23782 · 2026-08-26两阶段审议下的方向性修正：显示偏好分析
Directional Revision under Two-Horizon Deliberation: A Revealed-Preference Analysis
arXiv 2608.23781 · 2026-08-26一种利用Fourier–Mukai变换与二次型研究阿贝尔曲面中曲线的方法
An approach to curves in abelian surfaces using Fourier--Mukai and quadratic forms
arXiv 2608.23779 · 2026-08-26通过Calabi曲率算子刻画复射影空间
A characterization of complex projective space via the Calabi curvature operator
arXiv 2608.23778 · 2026-08-26关于秩二泊松猜想的一个明确反例
An Explicit Counterexample to the Rank-Two Poisson Conjecture
arXiv 2608.23777 · 2026-08-26用于预测性人类建模的解耦技能表示
Disentangled Skill Representations for Predictive Human Modeling
arXiv 2608.23776 · 2026-08-26
