2026-10论文中文摘要
CAT-Free：无需标定、标注或目标场景训练的自适应几何滤波多视角行人定位
CAT-Free: Multi-View Pedestrian Localization without Calibration, Annotations, or Target-Scene Training via Adaptive Geometric Filtering
arXiv 2609.34302 · 2026-10-01过度个性化是一种决策失败：LLMs中生成引发的应用偏差
Over-Personalization Is a Decision Failure: Generation-Induced Apply Bias in LLMs
arXiv 2609.34284 · 2026-10-01mmHRI：基于毫米波雷达的隐私保护人机交互
mmHRI: Towards Privacy-Preserving Human-Robot Interaction with Millimeter-Wave Radar
arXiv 2609.34220 · 2026-10-01行为锚定的语义增强用于金融欺诈建模与推理
Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning
arXiv 2609.34211 · 2026-10-01旋转标量场中对称性恢复的有限尺寸效应
Finite-Size Effects on Symmetry Restoration in a Rotating Scalar System with Spatially Dependent Thermal Self-Energy
arXiv 2609.34038 · 2026-10-01多数函数的最优浅层电路
Optimal Shallow Circuits for Majority
arXiv 2609.34029 · 2026-10-01RICE-Alpha：基于事件图与可靠性校正的LLM智能体股票预测
RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting
arXiv 2609.34004 · 2026-10-01多重并发提议者的地理激励研究
On the Geographic Incentives of Multiple Concurrent Proposers
arXiv 2609.33958 · 2026-10-01JET：Transformer中的论证评估
JET: Justification Evaluation in Transformer
arXiv 2609.33874 · 2026-10-01Riftbound 是图灵完备的
Riftbound is Turing Complete
arXiv 2609.33839 · 2026-10-01求解顶点完整性快于 $2^n$
Solving Vertex Integrity Faster than $2^n$
arXiv 2609.33779 · 2026-10-01AnyStep-WAM：面向世界动作模型的预算对齐蒸馏与自适应推理
AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models
arXiv 2609.33748 · 2026-10-01MomWorld：面向长时域自动驾驶的动量感知潜在世界模型
MomWorld: Momentum-Aware Latent World Model for Long-Horizon Autonomous Driving
arXiv 2609.33737 · 2026-10-01通过查询条件归因审计智能体行为
Auditing Agent Actions through Query-Conditioned Attribution
arXiv 2609.33676 · 2026-10-01CompoWorld：面向通用智能体的组合式环境扩展
CompoWorld: Compositional Environment Scaling for General Agents
arXiv 2609.33665 · 2026-10-01Reed--Solomon 码的向日葵
Sunflowers of Reed--Solomon Codes
arXiv 2609.33512 · 2026-10-01让CSP成为你的ANCHOR：基于冻结结构先验的自适应晶体搜索
Let CSP Be Your ANCHOR: Adaptive Crystal Search over Frozen Structure Priors
arXiv 2609.33407 · 2026-10-01估计不够：基于逐包均匀性检验的地毯式轰炸检测
Estimation is Not Enough: Carpet-Bombing Detection via Per-Packet Uniformity Testing
arXiv 2609.33308 · 2026-10-01精确性的极限：论自动微分在物理信息机器学习中的失效
The limits of exactness: On the failure of automatic differentiation in physics-informed machine learning
arXiv 2609.33078 · 2026-10-01对称零散度三维分段线性Filippov系统中可见-可见双折点的振荡动力学全局分类
Global classification of oscillatory dynamics in symmetric zero-divergence 3D piecewise-linear Filippov systems with a visible--visible two-fold
arXiv 2609.33034 · 2026-10-01通过原初黑洞的不对称捕获实现共振增强重子生成
Resonantly-Enhanced Baryogenesis through Asymmetric Capture by Primordial Black Holes
arXiv 2609.33031 · 2026-10-01TRACE：从ISAC测量中学习无线数字孪生的自校准
TRACE: Learning to Self-Calibrate Wireless Digital Twins from ISAC Measurements
arXiv 2609.32923 · 2026-10-01AnesTRACE：从多模态感知到多步决策的术中麻醉基准测试
AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making
arXiv 2609.32740 · 2026-10-01快速思考，选择性规划：面向高效数据驱动MPC的自适应深思
Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC
arXiv 2609.32591 · 2026-10-01飞行中KV缓存与干净锚点：加速自回归视频扩散
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
arXiv 2609.32540 · 2026-10-01Kolmogorov-Arnold 网络与多层感知机中的 Fisher 简单性
Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons
arXiv 2609.32503 · 2026-10-01SCLATE：持续学习智能体训练与评估的基础设施
SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation
arXiv 2609.32391 · 2026-10-01$2\times 2$ 三角布尔矩阵半环与关联半环的有限基问题
The finite basis problem for $2\times 2$ triangular Boolean matrix semirings and incidence semirings
arXiv 2609.32356 · 2026-10-01并非所有误差都重要：决策相关预测误差预测规划质量
Not All Errors Matter: Decision-Relevant Prediction Error Predicts Planning Quality
arXiv 2609.32322 · 2026-10-01氢，我的爱
Hydrogen mon amour
arXiv 2609.32307 · 2026-10-01免预填充跨家族KV缓存迁移：面向异构多智能体大语言模型
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
arXiv 2609.32259 · 2026-10-01指导而非回答：在策略内上下文蒸馏中使用指令特权
Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation
arXiv 2609.32201 · 2026-10-01宽带激光的联合幅度-相位优化将绝对双等离子体衰变阈值提升至相干时间预测之上
Joint Amplitude-Phase Optimization of Broadband Lasers Raises Absolute Two-Plasmon-Decay Thresholds Above Coherence-Time Predictions
arXiv 2609.31942 · 2026-10-01调制Bernal石墨烯中的Read-Rezayi分数量子霍尔绝缘体
Read-Rezayi fractional Chern insulators in modulated Bernal graphene
arXiv 2609.31846 · 2026-10-01透镜空间手术与Bleiler-Litherland猜想
Lens Space Surgeries and the Bleiler-Litherland Conjecture
arXiv 2609.31757 · 2026-10-01不要重复自己：面向覆盖率的自监督微调
Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage
arXiv 2609.31688 · 2026-10-01语言增强的视频动作预测：设计基础、基准与开放挑战
Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges
arXiv 2609.31665 · 2026-10-01面向联邦数据的可验证隐私学习
Toward provably private learning from federated data
arXiv 2609.31494 · 2026-10-01带状态约束的最优控制中的奇异倒向随机微分方程
Singular Backward SDEs for Optimal Control with State Constraints
arXiv 2609.31487 · 2026-10-01AxonSynth：用于光片显微镜中零样本3D轴突分割的域随机化合成数据
AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet Microscopy
arXiv 2609.31431 · 2026-10-01广义中心三项式系数的参数化 Catalan 型同余
A parametric Catalan-type congruence for generalized central trinomial coefficients
arXiv 2609.31423 · 2026-10-01分位数曲面的渐近形状
On the asymptotic shape of quantile surfaces
arXiv 2609.31345 · 2026-10-01液晶中短程序参量凝聚导致的纳米尺度调制的涌现
Emergence of Nanoscale Modulation in Liquid Crystals as a Result of Short-Range Order Parameter Condensation
arXiv 2609.30916 · 2026-10-01LLM帕金森综合征：执行控制失败、令牌低效持续行为，以及面向自主语言模型代理的不确定性感知全局执行控制架构
LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents
arXiv 2609.30662 · 2026-10-01HuGo：大型语言模型作为人形机器人全身策略代码设计器用于移动操作
HuGo: LLMs as Whole-Body Policy Code Designers for Humanoid Loco-Manipulation
arXiv 2609.30594 · 2026-10-01耗散孤子共振区弱光注入对噪声辅助多脉冲的能量选择性控制
Energy-selective control of noise-assisted multipulsing by weak optical seeding in the dissipative-soliton-resonance regime
arXiv 2609.30522 · 2026-10-01RAZOR：剪除大语言模型中可替换的专家
RAZOR: Pruning Replaceable Experts in LLMs
arXiv 2609.30465 · 2026-10-01信息论与代数重整化群
Informational and algebraic renormalization group
arXiv 2609.30362 · 2026-10-01非阿贝尔量子元胞自动机：$1{+}1$ 维 $SU(2)$ 杨-米尔斯理论（含费米子）
Non-abelian quantum cellular automata: $1{+}1$-dimensional $SU(2)$ Yang--Mills with fermions
arXiv 2609.30285 · 2026-10-01形成纠缠的Moreau-Yosida近似：基本性质与精度估计
The Moreau-Yosida approximation of the Entanglement of Formation: basic properties and accuracy estimates
arXiv 2609.30246 · 2026-10-01
