2026-09论文中文摘要
无激活导数的模拟友好预测编码
Analog-Friendly Predictive Coding without Activation Derivatives
arXiv 2609.32350 · 2026-09-29关于双曲（多项式）系统上的 $e$-双随机矩阵
On $e$-doubly stochastic matrices over hyperbolic (polynomial) systems
arXiv 2609.32349 · 2026-09-29图的K着色问题的量子框架
A Quantum Framework for K Coloring of Graphs
arXiv 2609.32348 · 2026-09-29观测 pristine 区域中的第三星族恒星
Observing population III stars in the pristine region
arXiv 2609.32347 · 2026-09-29面向人机协作的人体运动预测
Human Motion Prediction for Human-Robot Collaboration
arXiv 2609.32346 · 2026-09-29两相随机环境中的队列均衡加入策略
Equilibrium Joining Strategies for Queues in Two-Phase Random Environment
arXiv 2609.32345 · 2026-09-29ALLOT：面向大语言模型知识更新的预算化混合内存路由
ALLOT: Budgeted Hybrid-Memory Routing for Knowledge Updates in LLMs
arXiv 2609.32344 · 2026-09-29OpenMASC：加速MRI中跨轨迹金属感知采样与校正的开源流水线
OpenMASC: An Open-Source Pipeline for Cross-Trajectory Metal-Aware Sampling and Correction in Accelerated MRI
arXiv 2609.32343 · 2026-09-29饼状涡旋液滴在偶极分子玻色-爱因斯坦凝聚体中的研究
Pancake-shaped vortex droplets in dipolar molecular BECs
arXiv 2609.32342 · 2026-09-29注意力机制与状态空间模型在上下文学习中的比较分析
A Comparative Analysis of Attention versus State-Space Models for In-Context Learning
arXiv 2609.32341 · 2026-09-29SGA-Flow-GRPO：用于Flow-GRPO的空间梯度引导信用分配
SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO
arXiv 2609.32340 · 2026-09-29在技能检索前提供及时指导：在智能体上下文中保留有用的预热提示
Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context
arXiv 2609.32339 · 2026-09-29强制对exacting与ultraexacting基数的影响
The effects of forcing on exacting and ultraexacting cardinals
arXiv 2609.32338 · 2026-09-29拟阵约束下具有无差异关系的顶级交易循环机制
Top Trading Cycles with Indifferences under Matroid Constraints
arXiv 2609.32337 · 2026-09-29紧李群上最小秩椭圆结构的一个分解定理及其应用
A decomposition theorem for elliptic structures of minimal rank on compact Lie groups and applications
arXiv 2609.32335 · 2026-09-29可分Banach空间的对偶作为Calkin代数与泛型理想商
Duals of separable Banach Spaces as Calkin Algebras and Universal Ideal Quotients
arXiv 2609.32334 · 2026-09-29渐进视角在线蒸馏：多模态大语言模型从区域到全局的迁移
Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs
arXiv 2609.32333 · 2026-09-29当合并系数不再重要：面向持续LoRA适配的近邻正则化合并
When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
arXiv 2609.32332 · 2026-09-29语言距离对公平跨语言迁移具有实用性
Language Distances are Practical for Equitable Cross-Lingual Transfer
arXiv 2609.32331 · 2026-09-29逆极限检测包络作为 Calkin 代数
Inverse-Limit Detection Envelopes as Calkin Algebras
arXiv 2609.32330 · 2026-09-29精确的高温量子面积律
Exact High-Temperature Quantum Area Law
arXiv 2609.32329 · 2026-09-29扩散模型中的持续数据遗忘：基于转移的正则化方法
Continual Data Unlearning in Diffusion Models via Transition-based Regularization
arXiv 2609.32328 · 2026-09-29HyperReCo：利用超图神经网络检索并连接证据以支持LLM多跳推理
HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning
arXiv 2609.32327 · 2026-09-29RLHarness：通过强化学习协同进化程序性技能以进行长程多模态推理
RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning
arXiv 2609.32326 · 2026-09-29不完整训练数据下的主动特征获取
Active Feature Acquisition With Incomplete Training Data
arXiv 2609.32325 · 2026-09-2915年X射线研究将可变质量吸积与活动星系核NGC 7582的变脸行为联系起来
15-Year X-ray Study Links Variable Mass Accretion to Changing Look Behavior in AGN NGC 7582
arXiv 2609.32324 · 2026-09-29FoundDSR：一种基于引导式2D高斯溅射的可泛化深度超分辨率基础模型
FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution
arXiv 2609.32323 · 2026-09-29稳定自回归PDE基础模型滚动预测的事件触发上下文修复
Stabilizing Autoregressive PDE Foundation Model Rollouts with Event-Triggered Context Healing
arXiv 2609.32321 · 2026-09-29超维计算的叠加推理
Superposed Inference for Hyperdimensional Computing
arXiv 2609.32320 · 2026-09-29相空间注意力：Hairer 提升绕过单层归纳障碍
Phase Space Attention:A Hairer Lift Circumvents the Single-Layer Induction Obstruction
arXiv 2609.32319 · 2026-09-29排行榜能证明什么？面向生物医学文献综述智能体的公平评估与训练的组成可控性
What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents
arXiv 2609.32318 · 2026-09-29全板载：具有嵌入式CartPole仿真的全片上神经形态Q学习
All On-Board: Fully On-Chip Neuromorphic Q-Learning with Embedded CartPole Simulation
arXiv 2609.32317 · 2026-09-29一种感知，所有操作：面向操作级信号意图预测的方向性交通信号理解
One Perception, All Maneuvers: Directional Traffic Signal Understanding for Maneuver-Level Signal Intent Prediction
arXiv 2609.32316 · 2026-09-29从信号到轨迹：人类EEG和MEG中低维动力学入门指南
From Signals to Trajectories: A Primer on Low-Dimensional Dynamics in Human EEG and MEG
arXiv 2609.32315 · 2026-09-29对称排斥过程中渗流簇上等待时间分布的连续变化指数
Continuously varying exponents in the distribution of waiting times in the symmetric exclusion process on a percolation cluster
arXiv 2609.32314 · 2026-09-29MemTransfer：具身决策中超越匹配经验的记忆基准测试
MemTransfer: Benchmarking Memory Beyond Matched Experience in Embodied Decision-Making
arXiv 2609.32313 · 2026-09-29测试时语言模型的延迟监督
Delayed Supervision for Test-Time Language Models
arXiv 2609.32312 · 2026-09-29协变量依赖删失下半竞争风险数据的双重稳健估计
Doubly Robust Estimation under Covariate Dependent Censoring in Semi-Competing Risks Data
arXiv 2609.32311 · 2026-09-29守恒与弛豫模式使多项式成功的相干Carleman格子玻尔兹曼演化成为可能
Conserved and relaxing modes enable polynomial-success coherent Carleman lattice Boltzmann evolution
arXiv 2609.32310 · 2026-09-29PhiFold：基于物理结构协方差建模的动态蛋白质设计
PhiFold: Towards Dynamic Protein Design with Physics-Structured Covariance Modeling
arXiv 2609.32309 · 2026-09-29SparseDesign：精确编码序列设计的规模化扩展
SparseDesign: Scaling Exact Coding-Sequence Design
arXiv 2609.32308 · 2026-09-29NANOGrav 15年数据集中无可分辨源对超大质量黑洞双星系统的约束
Constraints on Supermassive Black Hole Binaries from the Lack of Resolvable Sources in the NANOGrav 15-yr Dataset
arXiv 2609.32306 · 2026-09-29无滑移边界条件在无网格格子玻尔兹曼方法中的斯托克斯流基准测试
Benchmark of no-slip boundary conditions for meshless Lattice Boltzmann Method in Stokes flow
arXiv 2609.32305 · 2026-09-29关于硬提示（Hard Prompt）的能力与局限
On the Capability and Limitation of Hard Prompt
arXiv 2609.32302 · 2026-09-29协同何时有助于主动特征获取？基于部分信息分解的研究
When Does Synergy Help Active Feature Acquisition? A PID-Based Study
arXiv 2609.32301 · 2026-09-29双曲空间中曲面的等变等距浸入
Equivariant isometric immersions of surfaces in hyperbolic space
arXiv 2609.32300 · 2026-09-29用于随机信号的ISAC DSP框架：从物理收发器到周期模型
A DSP Framework for ISAC with random signals: From Physical Transceiver to Periodic Models
arXiv 2609.32299 · 2026-09-29刷新还是实现？漂移模型中的计算分配
Refresh or Realize? Compute Allocation in Drifting Models
arXiv 2609.32298 · 2026-09-29Agentsensus：多智能体故事世界的共识压缩共享记忆
Agentsensus: Consensus-Compressed Shared Memory for Multi-Agent Story Worlds
arXiv 2609.32297 · 2026-09-29FUND：用于采样非归一化分布的密度流
FUND: Density Flow for Sampling Unnormalised Distributions
arXiv 2609.32296 · 2026-09-29
