2026-09论文中文摘要
基于全景图像的情节记忆具身问答中的信息性视角选择
Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images
arXiv 2609.33288 · 2026-09-29反馈使完美：NL到STL翻译的闭环框架
Feedback Makes Perfect: A Closed-Loop Framework for NL-to-STL Translation
arXiv 2609.33287 · 2026-09-29InfoEdit：探究信息图编辑中的全局布局推理
InfoEdit: Probing Global Layout Reasoning in Infographic Editing
arXiv 2609.33286 · 2026-09-29辐射尾场诱导双光子对产生阿秒极化正电子束的原位生成
In-situ Generation of Polarized Attosecond Positron Bunches via Radiation-Wakefield Induced Two-Photon Pairs
arXiv 2609.33285 · 2026-09-29RINI：看到先验是不够的
RINI: Seeing the Prior Is Not Enough
arXiv 2609.33284 · 2026-09-29梯形域上的加权 Bernstein 型不等式
Weighted Bernstein-type inequalities on a trapezoidal domain
arXiv 2609.33283 · 2026-09-29面向高流量应用中高效个性化主观判断的多维比较量表构建
Multi-Dimensional Comparative Scale Construction for Efficient Personalized Subjective Judgment in High-Traffic Applications
arXiv 2609.33282 · 2026-09-29应用无关的FPGA时钟分配网络电磁侧信道辐射
Application Agnostic EM Side-Channel Emanations of the FPGA Clock Distribution Network
arXiv 2609.33281 · 2026-09-29图像旁的文本：可信多模态医学数据中的检测、效用与泄漏及其更广泛领域
The Text Beside the Image: Detection, Utility and Leakage for Trustworthy Multimodal Medical Data and Beyond
arXiv 2609.33280 · 2026-09-29不规则时间序列中采样模式偏移下的域泛化
Domain Generalization under Sampling Pattern Shifts in Irregular Time Series
arXiv 2609.33279 · 2026-09-29过阻尼RLC电路中的制备控制弛豫：通向谱姆彭巴效应的教学路径
Preparation-controlled relaxation in an overdamped RLC circuit: A pedagogical route to the spectral Mpemba effect
arXiv 2609.33277 · 2026-09-29ChronoFlow: 用于不规则时间序列生成的分层流匹配
ChronoFlow: Hierarchical Flow Matching for Irregular Time Series Generation
arXiv 2609.33276 · 2026-09-29非厄米斯塔克局域化浴中的移动杂质动力学
Mobile-impurity dynamics in a non-Hermitian Stark-localised bath
arXiv 2609.33275 · 2026-09-29基于极限学习机的大跨桥梁非线性气动弹性荷载建模
Modelling non-linear aeroelastic loads in long-span bridges with extreme learning machines
arXiv 2609.33274 · 2026-09-29在错误设定结构下迈向可识别表示
Towards Identifiable Representations under Misspecified Structure
arXiv 2609.33273 · 2026-09-29下一个想法是分布：潜在空间中的生成式自回归推理
Next Thoughts Are Distributions: Generative Autoregressive Reasoning in the Latent Space
arXiv 2609.33271 · 2026-09-29结构化稀疏记忆用于循环推理
Structured Sparse Memory for Recurrent Reasoning
arXiv 2609.33270 · 2026-09-29Q-WAM：基于动作子空间保护的世界动作模型4比特量化
Q-WAM: 4-Bit Quantization of World Action Models with Action-Subspace Protection
arXiv 2609.33269 · 2026-09-29LSTMem：面向大型语言模型的分层长短期在线记忆
LSTMem: Hierarchical Long Short-Term Online Memory for Large Language Models
arXiv 2609.33268 · 2026-09-29Hayward黑洞的准正则模：从Schwarzschild到极端情形下的比较谱分析
Quasinormal modes of Hayward black holes from Schwarzschild to extremality: a comparative spectral analysis
arXiv 2609.33267 · 2026-09-29SIM辅助集成感知与隐蔽通信的鲁棒收发机设计
Robust Transceiver Design for SIM-Assisted Integrated Sensing and Covert Communications
arXiv 2609.33266 · 2026-09-29SCISSOR：面向管弦乐录音的乐谱条件乐器源分离
SCISSOR: Score-Conditioned Instrument Source Separation for Orchestral Recordings
arXiv 2609.33265 · 2026-09-29VehDyn：面向车辆动力学的驾驶世界模型基准
VehDyn: A Driving World Model Benchmark for Vehicle Dynamics
arXiv 2609.33264 · 2026-09-29树上字母表增长时的鲁棒重构
Robust Reconstruction on Trees with a Growing Alphabet
arXiv 2609.33263 · 2026-09-29混合近场与远场随机接入中活动检测的Majorization-Minimization框架
A Majorization-Minimization Framework for Activity Detection in Mixed Near-and-Far-Field Random Access
arXiv 2609.33262 · 2026-09-29EngIntervene：多模态工程状态理解与设计干预推理基准
EngIntervene: Benchmarking Multimodal Engineering State Understanding and Design Intervention Reasoning
arXiv 2609.33261 · 2026-09-29CORTEX：面向通用智能体的经验验证层
CORTEX: A Verified Experience Layer for Generalist Agents
arXiv 2609.33260 · 2026-09-29PORTER：边缘-云驻留用于持久三维场景图记忆
PORTER: Edge-Cloud Residency for Persistent 3D Scene Graph Memory
arXiv 2609.33258 · 2026-09-29两个头比一个好：聚合较弱的LLM以获得更好的预测
Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts
arXiv 2609.33257 · 2026-09-29ActionGround：冻结VLA策略的训练无关运行时精化
ActionGround: Training-Free Runtime Refinement of Frozen VLA Policies
arXiv 2609.33256 · 2026-09-29N×M版本编程用于量子软件：跨框架与引擎的高层组件
NxM-Version Programming for Quantum Software: High-Level Components across Frameworks and Engines
arXiv 2609.33255 · 2026-09-29BERT4DTI：基于BERT的药物-蛋白质相互作用预测模型
BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions
arXiv 2609.33254 · 2026-09-29VGGT-Diff：视觉几何与扩散模型结合用于稀疏视角新视角合成
VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis
arXiv 2609.33253 · 2026-09-29CascadeEP：注意力不平衡下MoE预填充的异步专家执行
CascadeEP: Asynchronous Expert Execution for MoE Prefill under Attention Imbalance
arXiv 2609.33252 · 2026-09-29在锗量子点中实现超过99.9%的高保真几何量子门
High-fidelity geometric quantum gates exceeding 99.9% in germanium quantum dots
arXiv 2609.33251 · 2026-09-29$n$ 体问题在所有维度中不存在无限自旋
No infinite spin in the $n$-body problem in all dimensions
arXiv 2609.33250 · 2026-09-29交换凝聚环上的宽子范畴
Wide subcategories over commutative coherent rings
arXiv 2609.33249 · 2026-09-29面向患者知识图谱的反馈鲁棒人工智能
Feedback-Robust AI for Patient Knowledge Graphs
arXiv 2609.33248 · 2026-09-29关于阈值原理、人工神经网络连接与计量经济学遗产的注记
A Note on Threshold Principle, Artificial Neural Network Connections and Econometric Legacy
arXiv 2609.33247 · 2026-09-29强化学习后验采样的极小极大最优性
Minimax-Optimality of Posterior Sampling for Reinforcement Learning
arXiv 2609.33246 · 2026-09-29声学进度传播用于ASR长程投机解码
Acoustic Progress Propagation for Long-Horizon Speculative Decoding in ASR
arXiv 2609.33245 · 2026-09-29ActiveMem：面向长时程智能体的动态潜在记忆树
ActiveMem: Dynamic Latent Memory Trees for Long-Horizon Agents
arXiv 2609.33244 · 2026-09-29CodeSkill：面向长程代码智能体的潜在技能抽象
CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents
arXiv 2609.33243 · 2026-09-29Hankel算子的强再生核定理与Garsia范数
The strong reproducing kernel thesis for Hankel operators and the Garsia norm
arXiv 2609.33242 · 2026-09-29Navier--Stokes--Maxwell 系统解的全局适定性与衰减估计
Global well-posedness and Decay estimates for solutions of the Navier--Stokes--Maxwell system
arXiv 2609.33241 · 2026-09-29局部性的代价：为何前向-前向算法不如反向传播？
The Price of Locality: Why Forward-Forward Underperforms Backpropagation?
arXiv 2609.33240 · 2026-09-29Schrödinger--Föllmer Actor--Critic：基于有限样本分析的扩散策略改进
Schrödinger--Föllmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis
arXiv 2609.33239 · 2026-09-29在 $(\alpha,L_0,L_1)$-光滑性下的信赖域方法复杂度分析
Complexity analysis of trust-region methods under $(α,L_0,L_1)$-smoothness
arXiv 2609.33238 · 2026-09-29SurgFlow：面向手术机器人操作的三维物体中心接触流
SurgFlow: 3D Object-Centric Contact Flow for Surgical Robot Manipulation
arXiv 2609.33237 · 2026-09-29基于触觉交互感知的物体中心表示学习用于机器人操作
Learning with Object-centric Representations of Tactile Interactive Perception for Robot Manipulation
arXiv 2609.33235 · 2026-09-29
