2026-07论文中文摘要
PLATO：用于智能体和任务开放性的指针学习者
PLATO: Pointer Learner for Agent and Task Openness
arXiv 2607.25082 · 2026-07-30单纯形解混：在对撞机中分离多种轻味喷注
Simplex Demixing: Disentangling Multiple Light-Flavor Jets at Colliders
arXiv 2607.24921 · 2026-07-30每个节点一个原子核的容错分布式量子计算
Fault-tolerant distributed quantum computing with a single nucleus per node
arXiv 2607.24907 · 2026-07-30超越“检索什么”：检索增强代码生成中的不确定性
Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation
arXiv 2607.24884 · 2026-07-30极值乔拉集及其线性类似物：使用联合科学家进行的人机数学研究
Extremal Chowla sets and their linear analogues: A human-AI mathematical investigation using Co-Scientist
arXiv 2607.24847 · 2026-07-30宇宙α粒子对月壤中反照率中子和γ射线产生的贡献：基于GEANT4模拟的计算研究
Contribution of cosmic alphas to generation of albedo neutrons and gammas in lunar regolith: A computational study based on GEANT4 simulations
arXiv 2607.24816 · 2026-07-30模型是否会在没有明确后果的情况下假装对齐？
Do Models Fake Alignment Without Clear Consequences?
arXiv 2607.24758 · 2026-07-30SADe：用于弱支持注释的少样本分割的稀疏原子支持净化
SADe: Sparse-Atom Support Decontamination for Few-Shot Segmentation with Weak Support Annotations
arXiv 2607.24706 · 2026-07-30库珀伯格六圆柱猜想的计算机辅助证明
A computer-assisted proof of Kuperberg's six-cylinder conjecture
arXiv 2607.24691 · 2026-07-30TRACE-CTI：利用知识图谱对TTP声明进行可审计的提取后治理
TRACE-CTI: Auditable Post-Extraction Governance of TTP Claims with Knowledge Graphs
arXiv 2607.24563 · 2026-07-30RemiAssist：一种用于痴呆症护理中基于照片的回忆疗法的治疗师支持系统
RemiAssist: A Therapist-Supporting System for Photo-Based Reminiscence Therapy in Dementia Care
arXiv 2607.24536 · 2026-07-30FilmBench：用于电影视频生成的电影级基准测试
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
arXiv 2607.24241 · 2026-07-30为什么贪心搜索能产生最优聚类结果？一种固定核心分配理论
Why does Greedy Search produce Optimal Clustering Outcomes? A Fixed-Core Assignment Theory
arXiv 2607.24237 · 2026-07-30基于阈值符号排序的基于大语言模型的源代码压缩
LLM-based Source Code Compression via Thresholded Symbol Ranking
arXiv 2607.24192 · 2026-07-30拟阵的Kazhdan - Lusztig多项式不一定是单峰的
Kazhdan-Lusztig polynomials of matroids need not be unimodal
arXiv 2607.24186 · 2026-07-30当前检索器涵盖了所有证据吗？联合跨页面检索的对照研究
Do Current Retrievers Cover All the Evidence? A Controlled Study of Conjunctive Cross-Page Retrieval
arXiv 2607.24165 · 2026-07-30Agent-UCT：应用于树的上置信界，用于具有成本意识的智能工作流优化
Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness
arXiv 2607.24162 · 2026-07-30通过无创脑成像在抓握和举起任务中同时解码动力学和运动学运动参数
Towards simultaneous decoding of kinetic and kinematic movement parameters during grasp and lift task by noninvasive brain imaging
arXiv 2607.24081 · 2026-07-30知晓的代价：一种超越静态排行榜的幻觉基准测试的资源感知协议
The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards
arXiv 2607.24063 · 2026-07-30AptAvatar：用于生产就绪头像的快速且生动的长格式音频驱动视频生成
AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars
arXiv 2607.24013 · 2026-07-30分时电价下电池更换的可扩展无缺货充电调度
Scalable No-Stockout Charging Scheduling for Battery Swapping Under Time-of-Use Prices
arXiv 2607.23922 · 2026-07-30通用热身路径：多条路线，一个指南针
The Universal Warmup Path: Automatic Preconditioner Selection for HMC
arXiv 2607.23788 · 2026-07-30合成孔径声呐上训练深度神经网络的数据增强方法比较
A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar
arXiv 2607.23770 · 2026-07-30LabRobFail：化学自动驾驶实验室中机器人故障分析的基准
LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory
arXiv 2607.23704 · 2026-07-30内涵类型论中的集合oids
Setoids in Intensional Type Theory
arXiv 2607.23671 · 2026-07-30计划以神秘的方式起作用：评估电子表格代理的计划模式
Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents
arXiv 2607.23670 · 2026-07-30图中的全外独立联盟
Total outer-independent coalition in graphs
arXiv 2607.23623 · 2026-07-30HiTMS：一个高通量多流语言隐写框架
HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework
arXiv 2607.23597 · 2026-07-30非官方FastLAS教程：程序员指南
An Unofficial FastLAS Tutorial: A Programmer's Guide
arXiv 2607.23557 · 2026-07-30大语言模型辩论在不同语言中重复论点的方式是否不同？
Do LLM Debates Repeat Arguments Differently Across Languages?
arXiv 2607.23442 · 2026-07-30方向影响函数：估计约束学习中的训练数据影响
Directional Influence Function: Estimating Training Data Influence in Constrained Learning
arXiv 2607.23388 · 2026-07-30粒子群优化中停滞定律的非高斯性
Non-Gaussianity of the Stagnation Law in Particle Swarm Optimization
arXiv 2607.23381 · 2026-07-30$^{15}$C非弹性$1/2^+ \rightarrow 5/2^+$激发：单粒子与集体过程
$^{15}$C inelastic $1/2^+ \rightarrow 5/2^+$ excitation: A single-particle versus a collective process
arXiv 2607.23291 · 2026-07-30LIGO-Virgo-KAGRA O4a 中具有亚太阳质量成分的双黑洞合并触发事件的参数估计
Parameter Estimation on LIGO-Virgo-KAGRA O4a Binary Merger Triggers with Sub-solar Mass Components
arXiv 2607.23119 · 2026-07-30连通线图的符号差无界
The signature of connected line graphs is unbounded
arXiv 2607.22874 · 2026-07-30LC-SEPLM：用于仅序列蛋白质表示学习的远程接触监督适应
LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning
arXiv 2607.22777 · 2026-07-30因果门控：用于Transformer模块剪枝的因果重要性蒸馏
CausalGate: Causal Importance Distillation for Transformer Module Pruning
arXiv 2607.22720 · 2026-07-30超越块边界：扩散大语言模型的多块编辑
Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models
arXiv 2607.22663 · 2026-07-30衬底-金属界面工程增强TaN/Ta薄膜超导谐振器性能
Substrate-metal interface engineering enhances TaN/Ta thin film superconducting resonator performance
arXiv 2607.22294 · 2026-07-30倾听，勿抄袭：内化音频基础的支架上下文以实现稳健的全模型语音理解
Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding
arXiv 2607.21943 · 2026-07-30中高频段地面-卫星下行共存的非相干检测与干扰对零
Noncoherent Detection and Interference Nulling for Terrestrial-Satellite Downlink Coexistence in the Upper Mid-Band
arXiv 2607.21838 · 2026-07-30任意温度下接近临界电流的超导薄膜中的热相位滑移
Thermal phase slips in superconducting films near the critical current at arbitrary temperatures
arXiv 2607.21801 · 2026-07-30数据流网络的松弛激活分析——一种用于机器学习和实时调度的时钟演算
Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling
arXiv 2607.21797 · 2026-07-30f(𝒦,ℛ)引力中的静态黑洞与Iyer-Wald熵
Static Black Holes and Iyer-Wald Entropy in $f(\mathcal{R},\mathcal{K})$ Gravity
arXiv 2607.21786 · 2026-07-30通过稳定流形方法求解磁流体动力学方程的磁弛豫
Magnetic relaxation for the MHD equations via the stable manifold method
arXiv 2607.21328 · 2026-07-30从核心坍缩超新星的千赫兹引力波信号探索标准模型之外的物理学
Exploring Physics beyond the Standard Model from kHz-Gravitational-Wave Signals of Core-Collapse Supernovae
arXiv 2607.20921 · 2026-07-30REFACT：用于紧凑且忠实的思维链推理的自适应事实重述
REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning
arXiv 2607.20833 · 2026-07-30关于无对称着色 \(k\) 项等差数列的着色问题的一个改进上界
An Improved Upper Bound for Colorings Without Symmetrically Colored $k$-Term Arithmetic Progressions
arXiv 2607.20752 · 2026-07-30自适应多时间尺度强化学习
Adaptive Multi-Horizon Reinforcement Learning
arXiv 2607.20656 · 2026-07-30推动全曲生成的前沿：分层自回归规划与流匹配渲染
Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering
arXiv 2607.20253 · 2026-07-30
