2026-09论文中文摘要
SparseDitto：基于大语言模型的智能体系统，为不同稀疏性模式定制GPU内核
SparseDitto: An Agentic Sparse Compilation Framework through Architecture-Aware Synthesis on GPUs
arXiv 2608.05033 · 2026-09-11解析致密光解离区：三维气体分布中光化学前沿的结构
Resolving dense photodissociation regions: the structure of photochemical fronts in three-dimensional gas distributions
arXiv 2608.04116 · 2026-09-11有限赋值可逼近结构：概率幂域的Jung–Tix问题的一个解决方案
Finite-valuation approximable structures: a solution to the Jung--Tix problem of probabilistic powerdomains
arXiv 2608.03073 · 2026-09-11一类面积型Mahler测度的积分表示与渐近行为
Integral Representations and Asymptotics for a Family of Areal Mahler Measures
arXiv 2608.01951 · 2026-09-11SPECTRA：用于地理空间基础模型跨传感器微调的波段路由嵌入与分阶段LoRA
SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models
arXiv 2608.01751 · 2026-09-11一维PT对称双色光学晶格中弱排斥玻色-爱因斯坦凝聚体的莫尔平带的命运
Fate of moiré flat bands for a weakly repulsive Bose-Einstein condensate in one-dimensional $\mathcal{PT}$-symmetric bichromatic optical lattices
arXiv 2608.01680 · 2026-09-11基于强化学习的智能体技能渐进式生成
Progressive Agent Skill Generation via Reinforcement Learning
arXiv 2608.01678 · 2026-09-11锚定盒的渐近最优 bracketing 覆盖
Asymptotically optimal bracketing covers for anchored boxes with applications to star discrepancy
arXiv 2608.00899 · 2026-09-11面向LLM智能体的优先执行式合成工具使用轨迹生成
Execution-First Synthetic Tool-Use Trace Generation for LLM Agents
arXiv 2607.29175 · 2026-09-113-均匀超图中不同极大团的大小
On the distinct maximal-clique sizes in $k$-uniform hypergraphs
arXiv 2607.27837 · 2026-09-11共情框架：跨社会人口统计群体评估AI对齐
Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
arXiv 2607.27232 · 2026-09-11自旋轨道转矩的隐藏伙伴
Current-Driven Magnetization Switching via Zhang-Li Torque
arXiv 2607.26392 · 2026-09-11HeteroPROPMT：一种实时且隐私保护的异构协同感知框架
HeteroPROMPT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework
arXiv 2607.26283 · 2026-09-11SET-ANUBIS：用于ANUBIS长寿命粒子灵敏度研究的模块化流程
SET-ANUBIS: a modular pipeline for ANUBIS long-lived particle sensitivity studies
arXiv 2607.26112 · 2026-09-11用于锂金属电解质中官能团和盐效应电子结构分析的密度矩阵框架
A Density-Matrix Framework for Electronic-Structure Analysis of Electrolytes for Lithium Batteries
arXiv 2607.25597 · 2026-09-11ScaleResfusion：基于残差向量场的残差整流流
ScaleResfusion: Residual Rectified Flow based on Residual Vector Field
arXiv 2607.25275 · 2026-09-11高能核碰撞中的少胶子相互作用和多极辐射
Few-gluon interactions and multipole radiation in high energy nuclear collisions
arXiv 2607.25017 · 2026-09-11设计矩阵的零模式驱动过参数化回归中的多重下降
The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression
arXiv 2607.24041 · 2026-09-11数值半群多参数计数的算法与结果
Multiparameter counting of numerical semigroups: recurrences and leaf-discriminating trees
arXiv 2607.23111 · 2026-09-11使用语法书进行低资源机器翻译合成数据生成的析因研究
A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books
arXiv 2607.22376 · 2026-09-11关于张量特征值重数的新猜想
New conjectures on multiplicities of tensor eigenvalues
arXiv 2607.21422 · 2026-09-11相同博弈，不同故事：大语言模型智能体的最小保守战略稳健性基准
Same Game, Different Story: A Minimal Conservative Strategic Robustness Benchmark for Large Language Model Agents
arXiv 2607.19670 · 2026-09-11SGA：用于教育视频合成的即插即用几何验证
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
arXiv 2607.18116 · 2026-09-11自然语言访问特定领域元数据：用于大语言模型查询生成的可重用框架
Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation
arXiv 2607.18029 · 2026-09-11平面N = 4超杨-米尔斯中奇数共形自旋下的次下领先阶BFKL本征值
The next-to-next-to-leading order BFKL eigenvalue at odd conformal spin in planar N=4 super Yang-Mills
arXiv 2607.17608 · 2026-09-11使随机变量对称化需要多少随机性？
Symmetrization resistance for exponential and geometric distributions
arXiv 2607.17576 · 2026-09-11学生对同伴互评的看法
Students' Perceptions of Peer Grading
arXiv 2607.16221 · 2026-09-11模型实际看到了什么？数据驱动的房间声学参数预测中的评估协议和输入可用性
What does the model actually see? Evaluation protocols and input availability in data-driven prediction of room acoustic parameters
arXiv 2607.15243 · 2026-09-11关于素数乘积上指数和的Bombieri- Vinogradov定理
A Bombieri-Vinogradov theorem for exponential sums over products of k primes
arXiv 2607.15137 · 2026-09-11玻色子SPT和可逆相及其与施泰因罗德问题的关系
Bosonic SPT and invertible phases and its relation to Steenrod's problem
arXiv 2607.14662 · 2026-09-11非厄米全息流向小撕裂宇宙学
Non-Hermitian Holographic Flows to Little Rip Cosmologies
arXiv 2607.14284 · 2026-09-11关于随机设计下可达到的速率：对罗宾斯一个问题的否定回答
Nearly-minimax variance estimation under rough random design
arXiv 2607.13170 · 2026-09-11EVOQUANT：用于稳健量化交易的自进化验证器引导策略优化
EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading
arXiv 2607.12455 · 2026-09-11（早期）人工智能计算资产定价
(Early) AI Compute Asset Pricing
arXiv 2607.12156 · 2026-09-11从超子 - 核子相互作用到氘核 - 超子的飞米学
From hyperon--nucleon interactions to deuteron--hyperon femtoscopy
arXiv 2607.10722 · 2026-09-11对于秩宽至多为二的图，可识别性等同于CMSO可定义性
Recognizability equals CMSO-definability for graphs of rank-width at most two
arXiv 2607.10594 · 2026-09-11印度在不确定性下的可承受低碳电力路径
A multi-model framework for identifying affordable low-carbon electricity pathways for India under uncertainty
arXiv 2607.10581 · 2026-09-11激光中最小可测频移的一般量子极限及优化
The General Quantum Limit for and the Optimization of the Minimum Measurable Frequency Shift in a Laser
arXiv 2607.10518 · 2026-09-11平坦扩张下的 Buchsbaum 模与参数理想
Buchsbaum modules and parameter ideals under flat extensions
arXiv 2607.10393 · 2026-09-11RDQ：大语言模型的残差分布量化
RDQ: Residual Distribution Quantization for Large Language Models
arXiv 2607.10137 · 2026-09-11YOLO26在边缘部署方面真的比其前身更具优势吗？水产养殖中的基准研究
Does YOLO26 Truly Offer Advantages Over Its Predecessors for Edge Deployment? A Benchmark Study in Aquaculture
arXiv 2607.09835 · 2026-09-11通过有限规则修订验证自适应智能体控制器
Verification of Adaptive Agentic Controllers through Finite Rule Revision
arXiv 2607.09770 · 2026-09-11这不是一支烟斗：作为语义抽象的人工智能系统
Ceci n'est pas une pipe: AI systems as semantic abstractions
arXiv 2607.09489 · 2026-09-11冰充电对非晶态固态水上星际含硫物种天体化学的影响
Effect of Ice Charging on the Astrochemistry of Interstellar Sulfur Bearing Species on Amorphous Solid Water
arXiv 2607.09364 · 2026-09-11ProsMAE：用于ISUP分级分类的多源MAE预训练
ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification
arXiv 2607.08162 · 2026-09-11DiaLLM：英语方言适应中稳健性-生成差距的研究
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
arXiv 2607.07669 · 2026-09-11双矩阵博弈中具有非对称步长的乐观指数权重的稳定性与收敛性
Stability and Convergence of Optimistic Exponential Weights with Asymmetric Step Sizes in Bimatrix Games
arXiv 2607.07517 · 2026-09-11来自黑盒密码学的带预处理的私有信息检索的下界
Lower Bounds for PIR with Preprocessing from Blackbox Cryptography
arXiv 2607.06451 · 2026-09-11SafeImpute：通过共形选择实现可靠的临床数据插补
SafeImpute: Reliable Clinical Data Imputation via Conformal Selection
arXiv 2607.05613 · 2026-09-11具有哈尔随机硬币算子的d正则图上的量子随机游走
Quantum random walks on d-regular graphs with Haar-random coin operators
arXiv 2607.04584 · 2026-09-11
