2026-09论文中文摘要
JIVE：基于雅可比信息的体积扩展用于多样化生成采样
JIVE: Jacobian-Informed Volume Expansion for Diverse Generative Sampling
arXiv 2609.33906 · 2026-09-29SlopBench：我们能在多大程度上根据“AI 废料”对语言模型进行排序？一个多领域的重复性 AI 写作基准
SlopBench: How Well Can We Rank Language Models by Slop? A Multi-Domain Benchmark of Repetitive AI Writing
arXiv 2609.33905 · 2026-09-29Adam在可分离线性分类中的两面性
On the Two Faces of Adam in Separable Linear Classification
arXiv 2609.33904 · 2026-09-29提示词匿名能否保护您的身份免受大语言模型提供商的侵害？
Can Prompt Anonymity Protect Your Identity From LLM Providers?
arXiv 2609.33903 · 2026-09-29Det-极值三次图与全支配数
Det-extremal cubic graphs and the total domatic number
arXiv 2609.33902 · 2026-09-29单调混合与分布动力学
Monotone Mixing and Distribution Dynamics
arXiv 2609.33900 · 2026-09-29NSV-Shift：用于语音到语音模型中非言语发声理解与响应适应的对比基准
NSV-Shift: A Contrastive Benchmark for Non-Speech Vocalization Understanding and Response Adaptation in Speech-to-Speech Models
arXiv 2609.33899 · 2026-09-29没有免费的效率：重新审视训练效率与模型脆弱性之间的权衡
No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability
arXiv 2609.33898 · 2026-09-29混合噪声即插即用：基于下确卷积保真项与多先验的算法
Mixed-Noise Plug-and-Play with Infimal Convolution Fidelities and Multiple Priors
arXiv 2609.33897 · 2026-09-29行为的调和理论
Harmonic Theory of Behavior
arXiv 2609.33896 · 2026-09-29调制空间：从Feichtinger的原始定义到现代Gabor与辛刻画
Modulation spaces: from Feichtinger's original definition to modern Gabor and symplectic characterizations
arXiv 2609.33894 · 2026-09-29MISHAP-Bench：大型音频语言模型的幻觉基准
MISHAP-Bench: A Hallucination Benchmark for Large Audio-Language Models
arXiv 2609.33893 · 2026-09-29基于残差学习的车辆队列控制与 $\ell_2$ 稳定性保证：利用循环均衡网络
Residual Learning-Based Control of Vehicle Platoons with $\ell_2$ Stability Guarantees via Recurrent Equilibrium Networks
arXiv 2609.33892 · 2026-09-29用于多校准的增强特征提升
Augmented Feature Boosting for Multicalibration
arXiv 2609.33891 · 2026-09-29FIID 染色随机映射
FIID Coloring Random Maps
arXiv 2609.33890 · 2026-09-29激活稀疏化与KV缓存稀疏化在LLM解码中的交叉点
Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding
arXiv 2609.33889 · 2026-09-29香草策略优化在随机上下文赌博机中既最优又具有差分隐私
Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits
arXiv 2609.33888 · 2026-09-29更快的块扩散推理服务，具有无分布风险保证
Faster Block-Diffusion Serving with Distribution-Free Risk Guarantees
arXiv 2609.33887 · 2026-09-29前瞻性解释风险：大语言模型之间的原则性通信控制
Prospective Interpretation Risk: Principled Communication Control Between LLMs
arXiv 2609.33885 · 2026-09-29Qin关于点的Hilbert概形的拟模性猜想
Qin's quasimodularity conjecture for Hilbert schemes of points
arXiv 2609.33884 · 2026-09-29带着地图迷路：语言模型中的对话状态与行为可靠性
Lost with a Map: Conversational State and Behavioral Reliability in Language Models
arXiv 2609.33883 · 2026-09-29DexTaG：触觉作为灵巧操作强化学习中的引导
DexTaG: Tactile-as-Guidance in Reinforcement Learning for Dexterous Manipulation
arXiv 2609.33882 · 2026-09-29通过高维中介分析理解行业对关税不确定性的响应
Understanding Sectoral Responses to Tariff Uncertainty via a High-Dimensional Mediation Analysis
arXiv 2609.33881 · 2026-09-29神经元级架构增长：针对EEG时间序列解码的受控评估
Neuron-Level Architecture Growth: A Controlled Evaluation for EEG Time-Series Decoding
arXiv 2609.33880 · 2026-09-29DCEmbed：神经代理模型的可扩展优化
DCEmbed: Scalable Optimization over Neural Surrogates
arXiv 2609.33879 · 2026-09-29通过太阳中微子振荡约束超轻矢量玻色子：规范 $L_\mu - L_\tau$ 模型及 JUNO 与 XLZD 的前景展望
Constraining Ultra-Light Vector Bosons via Solar Neutrino Oscillations: The Gauged $L_μ- L_τ$ Model and Prospects for JUNO and XLZD
arXiv 2609.33877 · 2026-09-29Bourgain--Brezis 选择映射在 Besov 与 Triebel--Lizorkin 空间中的 Hodge 系统
Bourgain--Brezis selection maps for Hodge systems in Besov and Triebel--Lizorkin spaces
arXiv 2609.33876 · 2026-09-29CSP的紧致性原理与选择公理
Compactness Principles for CSPs and the Axiom of Chocie
arXiv 2609.33873 · 2026-09-29Robot-GST：几何感知的时空机器人策略表示与评估
Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluation
arXiv 2609.33872 · 2026-09-29群体物理学，群体问题：LLM 社会中的安全性与涌现性
Population Physics, Population Problems: Safety and Emergence in LLM Societies
arXiv 2609.33871 · 2026-09-29当成功策略失效：终端智能体对环境新颖性的适应
When Successful Strategies Fail: Adaptation to Environmental Novelty in Terminal Agents
arXiv 2609.33870 · 2026-09-29时间序列的共形覆盖：有效性与推断
Conformal Coverage of Time Series: Validity and Inference
arXiv 2609.33868 · 2026-09-29R$^2$ Flow：通过递归技能进化实现递归自我改进
R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution
arXiv 2609.33867 · 2026-09-29时间序列的有效且高效的分割保形回归
Valid and Efficient Split Conformal Regression for Time Series
arXiv 2609.33866 · 2026-09-29编码器-解码器模型在语音识别中的上下文自适应
In-Context Adaptation of Encoder-Decoder Models in Speech Recognition
arXiv 2609.33865 · 2026-09-29以同行评审换取发表：信息技术领域免费、基于信用的开放获取期刊的设计与模拟
Paying for Publication with Peer Review Design and Simulation of a Fee-Free, Credit-Based Open Access Journal for Information Technology
arXiv 2609.33864 · 2026-09-29一维斐波那契准晶的交互式环面参数化
Interactive Torus Parametrization of the One-Dimensional Fibonacci Quasicrystal
arXiv 2609.33863 · 2026-09-29结构光的Hong-Ou-Mandel干涉非线性工程
Nonlinear engineering of Hong-Ou-Mandel interference with structured light
arXiv 2609.33862 · 2026-09-29夜间灯光与日本各项统计指标之间的相关性
Correlation Between Nighttime Light and Various Statistical Indicators in Japan
arXiv 2609.33861 · 2026-09-29固定业务与6G移动网络频谱共享场景中的干扰分析
Interference Analysis in Spectrum Sharing Scenarios between Fixed Services and 6G Mobile Networks
arXiv 2609.33860 · 2026-09-29夜间灯光影像用于详细地方经济分析的潜力
The Potential of Nighttime Light Imagery for Detailed Local Economic Analysis
arXiv 2609.33859 · 2026-09-29Vicsek 集上的 Riesz 变换
Riesz transforms on the Vicsek set
arXiv 2609.33858 · 2026-09-29PI-NOMT：面向脑部流体动力学的物理信息神经最优质量传输
PI-NOMT: Physics-Informed Neural Optimal Mass Transport for Brain Fluid Dynamics
arXiv 2609.33857 · 2026-09-29选择原理与不可数情形下的Scheepers图
Selection principles and the Scheepers diagram in an uncountable setting
arXiv 2609.33856 · 2026-09-29程序验证的视觉语言模型自我进化
Program-Verified Self-Evolution for Vision-Language Models
arXiv 2609.33855 · 2026-09-29ReDrive：通过世界建模塑造表征以实现端到端驾驶
ReDrive: Shaping Representations with World Modeling for End-to-End Driving
arXiv 2609.33854 · 2026-09-29统一目标说话人语音识别：基于文本与注册语音线索
Unified Target-Speaker ASR with Text and Enrollment Speech Cues
arXiv 2609.33853 · 2026-09-29高阶平均场控制障碍函数
Higher-Order Mean-Field Control Barrier Functions
arXiv 2609.33852 · 2026-09-29重新思考上下文化：通过重新解读注意力头通道
Rethinking Contextualization by Reinterpreting Attention Head Channels
arXiv 2609.33851 · 2026-09-29互联网与企业战略再审视：从数字连接到AI赋能企业，1996-2026
Internet and Enterprise Strategy Revisited: From Digital Connectivity to AI-Enabled Enterprises, 1996 - 2026
arXiv 2609.33850 · 2026-09-29
