2026-08论文中文摘要
MirrorWorld：利用视频扩散模型生成镜像反射
MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation
arXiv 2608.07463 · 2026-08-10SemBridge：用于连续隐变量自回归语音生成的语义令牌锚定
SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation
arXiv 2608.07462 · 2026-08-10自行运动的清晰探测证实，被声称的红移z≃32的星系候选体“Capotauro”是一颗Y型褐矮星
A clear detection of proper motion confirms that the claimed $\mathbf{z\simeq32}$ galaxy candidate, "Capotauro'', is a Y-type brown dwarf
arXiv 2608.07461 · 2026-08-10CreativeInstruct：规模化教导大型语言模型（LLM）平衡质量、创造性与多样性
CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
arXiv 2608.07460 · 2026-08-10自同构下的双无瑕函数的相等性
Equality of Dual Immaculate Functions Under Automorphisms
arXiv 2608.07459 · 2026-08-10CoinRAG：面向长上下文RAG的上下文信息 nugget KV缓存复用
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
arXiv 2608.07458 · 2026-08-10交互产生孤立状态下不存在的动态AI行为
Interaction Creates Dynamical AI Behavior Absent in Isolation
arXiv 2608.07457 · 2026-08-10用于暗物质搜寻的双碱金属共磁计中核子耦合比的最优无校准可观测量
Optimal Calibration-Free Observable for the Nucleon-Coupling Ratio in a Dual-Alkali Comagnetometer for Dark Matter Searches
arXiv 2608.07456 · 2026-08-10红巨星恒星间歇性质量抛射产生的白矮星 kick
White Dwarf Kicks via Episodic Mass Ejection from Red Giant Stars
arXiv 2608.07455 · 2026-08-10复杂天然产物的优先策略合成规划
Strategy-first synthesis planning for complex natural products
arXiv 2608.07454 · 2026-08-10下一代宇宙微波背景巡天对中微子及其他轻遗迹的灵敏度
Sensitivity of Next-Generation CMB Surveys to Neutrinos and Other Light Relics
arXiv 2608.07453 · 2026-08-10反对法律领域的可解释人工智能：为何正当的人工智能至关重要——以信用评分为例
Against Explainable Artificial Intelligence In Law: Why Justifiable Ai Matters. A Credit Scoring Example
arXiv 2608.07452 · 2026-08-10野生环境中钓鱼工具包（Phishkits）的架构与运行动态分析
An Analysis of Architectural and Operational Dynamics of Phishkits in the Wild
arXiv 2608.07451 · 2026-08-10主动Cahn-Hilliard方程的数值分析与粗化动力学
Numerical analysis and coarsening dynamics of the Active Cahn-Hilliard equation
arXiv 2608.07450 · 2026-08-10SkillProx：基于近端文本梯度下降的自进化智能体技能
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
arXiv 2608.07449 · 2026-08-10觅食海龟的主动运动产生异常环路
Active movement of foraging sea turtles generates anomalous looping
arXiv 2608.07448 · 2026-08-10$\Pi$-对称超长程里德堡分子的观测
Observation of $Π$-symmetry ultralong-range Rydberg molecules
arXiv 2608.07447 · 2026-08-10分类驱动的开源AI风险缓解工具分析
Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools
arXiv 2608.07446 · 2026-08-10面心立方高熵合金在变形及变化化学环境下空位形成的排列不变性神经网络预测
Permutation invariant neural network prediction of vacancy formation under deformation and varying chemical environment in FCC high entropy alloys
arXiv 2608.07445 · 2026-08-10基于波束域机器学习指纹的、存在跨链路干扰的智能反射面辅助毫米波定位
RIS-Aided mmWave Localization Under Cross-Link Interference via Beam-Domain ML Fingerprinting
arXiv 2608.07444 · 2026-08-10手性畴壁亚稳态的量子几何机制：在扭曲过渡金属二硫族化合物中的应用
A quantum geometric mechanism for chiral domain wall metastability: Application to twisted transition-metal dichalcogenides
arXiv 2608.07443 · 2026-08-10光晶格中由相位噪声诱导的加热效应
Phase-Noise-Induced Heating in Optical Lattices
arXiv 2608.07442 · 2026-08-10利用测量发散高次谐波的平面刻线反射光栅光谱仪主动控制极紫外光子通量与分辨率
Active Control of Extreme Ultraviolet Photon Flux and Resolution with a Plane Ruled Reflection Grating Spectrometer that Measures Diverging High-Harmonics
arXiv 2608.07441 · 2026-08-10基于DisCoCat的情感分析中，大语言模型辅助改写中等复杂度金融句子的探索性评估
An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis
arXiv 2608.07439 · 2026-08-10Fisher-R1：训练用于可靠假设检验的大语言模型智能体
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
arXiv 2608.07437 · 2026-08-10SABRE：压力场景下视觉语言模型（VLM）的可扩展自动化基准测试
SABRE: Scalable and Automated Benchmarking of VLMs under Stress
arXiv 2608.07435 · 2026-08-10任意视频时间定位器的共形覆盖保证
Conformal Coverage Guarantees for Any Video Temporal Grounder
arXiv 2608.07434 · 2026-08-10熵正则化线性二次控制的Wasserstein策略梯度
Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control
arXiv 2608.07433 · 2026-08-10凸正则化的谱依赖：右旋转不变设计下的基本极限
Spectral Dependence of Convex Regularization: Fundamental Limits under Right-Rotationally Invariant Designs
arXiv 2608.07432 · 2026-08-10扩散大语言模型作为目标与对抗者：机制性安全漏洞利用
Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
arXiv 2608.07430 · 2026-08-10QMIMO：基于电路的量子MIMO设计与变分接收机
QMIMO: Circuit Based Quantum MIMO Design with Variational Receiver
arXiv 2608.07428 · 2026-08-10一图胜千词：视觉语言模型如何在提升准确率的同时降低AI能源成本
A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy
arXiv 2608.07427 · 2026-08-10利用连续谱中的束缚态实现氮化硅微腔中的量子与非线性光子学
Harnessing bound states in the continuum for quantum and nonlinear photonics in silicon nitride microresonators
arXiv 2608.07426 · 2026-08-10放手还是介入？领域主席实践的差异及其对AI支持的意义
Hands-Off or Hands-On? Variation in Area Chair Practices and Implications for AI Support
arXiv 2608.07425 · 2026-08-10超越近视世界模型：面向直接未来预测的长视端到端训练
Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
arXiv 2608.07420 · 2026-08-10超越事后温度缩放：用于大语言模型校准的双层优化方法
Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration
arXiv 2608.07419 · 2026-08-10ResidencyRL：在模拟临床环境中开展的强化学习
ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
arXiv 2608.07418 · 2026-08-10我在视频中寻找你：面向以人为中心的视频推理的身份条件查询
I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning
arXiv 2608.07417 · 2026-08-10贝叶斯公平分配：具有相关估值的选取序列中的真实性
Bayesian Fair Division: Truthfulness in Picking Sequence with Correlated Valuations
arXiv 2608.07414 · 2026-08-10可移动天线系统的高效离散位置设计：低复杂度与鲁棒性
Efficient Discrete Position Design for Movable Antenna Systems: Low Complexity and Robustness
arXiv 2608.07413 · 2026-08-10GeoBenchLLM：评估大语言模型地理相关任务的综合基准
GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks
arXiv 2608.07411 · 2026-08-10有界密度次高斯项的随机行子矩阵的极小奇异值
Extreme least singular values of random row submatrices with bounded-density subgaussian entries
arXiv 2608.07410 · 2026-08-10UniJEPA：面向任务无关视觉世界建模的统一联合嵌入预测架构
UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling
arXiv 2608.07409 · 2026-08-10视频世界模型的可寻址内存
Addressable Memory for Video World Models
arXiv 2608.07408 · 2026-08-10面向优化研究端到端自动化的领域专用工具链
A Domain-Specific Harness for End-to-End Automation of Optimization Research
arXiv 2608.07407 · 2026-08-10评估地球科学回归任务的可解释人工智能方法：来自应用与Lorenz-63系统的见解
Evaluating Explainable AI Methods for Geoscientific Regression: Insights from Applications and the Lorenz-63 System
arXiv 2608.07406 · 2026-08-10GeoDistill-Refine：面向无标注航天器分割的基于轮廓优先的几何蒸馏方法
GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation
arXiv 2608.07405 · 2026-08-10利用洛伦兹 boost 算子方法简化对 Sunyaev-Zeldovich（SZ）效应的运动学修正处理
Simplified treatment of kinematic corrections to the SZ effect using the boost operator approach
arXiv 2608.07404 · 2026-08-10基于细胞数量数据的免疫系统网络拓扑推断
Topology Inference for Immune System Networks by Using Cell Amount Data
arXiv 2608.07403 · 2026-08-10具有规定最大度的极大σ-不规则树的完整刻画
A complete characterization of maximally σ-irregular trees with prescribed maximum degree
arXiv 2608.07402 · 2026-08-10
