2026-09论文中文摘要
$p$-Laplacian 的 Heintze--Karcher 型不等式与 Serrin 型刚性
Heintze--Karcher-Type Inequalities for the $p$-Laplacian and Serrin-Type Rigidity
arXiv 2609.34252 · 2026-09-29RADNPO：用于大语言模型机器遗忘的无参考自适应负偏好优化
RADNPO: Reference-free Adaptive Negative Preference Optimization for LLM Unlearning
arXiv 2609.34251 · 2026-09-29WAM-OPD：通过在线策略蒸馏锐化世界动作模型
WAM-OPD: Sharpening World Action Models via On-Policy Distillation
arXiv 2609.34250 · 2026-09-29共情强化学习中的支持优先级演化
Evolving Support Priorities in Empathetic Reinforcement Learning
arXiv 2609.34249 · 2026-09-29BKT流中的RG极限环 $\equiv$ 电流-电流微扰$SU(2)_1$ WZW模型中的周期性实时动力学
RG Limit Cycles in BKT Flows $\equiv$ Periodic Real-Time Dynamics in the Current-Current Perturbed $SU(2)_1$ WZW Model
arXiv 2609.34248 · 2026-09-29SALMONN-duo：用于全双工语音代理的自适应双系统协调
SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents
arXiv 2609.34247 · 2026-09-29CasEm：用于长时程神经仿真级联架构
CasEm: A Cascade Architecture for Long-Horizon Neural Emulation
arXiv 2609.34246 · 2026-09-29结构化智能体动作的认证多源完整性
Certified Multi-Source Integrity for Structured Agent Actions
arXiv 2609.34245 · 2026-09-29当模型选择问题：自下而上多智能体探究中的教学约束
When Models Choose the Question: Pedagogical Constraints in Bottom-Up Multi-Agent Inquiry
arXiv 2609.34243 · 2026-09-29Stashbird：面向对话代理的高效说话人索引记忆系统
Stashbird: Efficient Speaker-Indexed Memory for Conversational Agents
arXiv 2609.34242 · 2026-09-29AdaGuard：具有用户自定义策略的自适应防护模型
AdaGuard: An Adaptive Guard Model with User-defined Policies
arXiv 2609.34241 · 2026-09-29用拉格朗日插值方法重建减速参数的演化
Reconstructing the evolution of deceleration parameter with the Lagrange interpolation method
arXiv 2609.34239 · 2026-09-29全非线性奇异椭圆方程的边界正则性
Boundary Regularity for Fully Nonlinear Singular Elliptic Equations
arXiv 2609.34238 · 2026-09-29DecFlowEdit：通过引导解耦实现自定位的基于流的图像编辑
DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling
arXiv 2609.34237 · 2026-09-29计算循环凸性中的 Helly 数、Radon 数和秩
Computing the Helly Number, Radon Number and Rank in Cycle Convexity
arXiv 2609.34236 · 2026-09-29SegBanana：将统一多模态模型引导为医学分割器
SegBanana: Steering Unified Multimodal Models into Medical Segmenters
arXiv 2609.34235 · 2026-09-29MAS-OPD：多智能体系统的在线策略蒸馏
MAS-OPD: On-Policy Distillation for Multi-agent Systems
arXiv 2609.34234 · 2026-09-29GAE：用于实时人形机器人遥操作的一般动作专家
GAE: General Action Expert for Real-Time Humanoid Teleoperation
arXiv 2609.34233 · 2026-09-29可信的合成视觉媒体：贯穿媒体生命周期的证据
Trustworthy synthetic visual media: Evidence across the media lifecycle
arXiv 2609.34232 · 2026-09-29ReGDiff：调控潜空间中的引导扩散用于探索超材料体素几何
ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry
arXiv 2609.34231 · 2026-09-29anapole 和 charge-radius 非弹性暗物质的 freeze-in 产生：退耦矢量门户的 X 射线探针
Freeze-in of anapole and charge-radius inelastic dark matter: X-ray probes of a decoupled vector portal
arXiv 2609.34230 · 2026-09-29基于大语言模型的推荐系统中身份线索偏好漂移的测量与缓解
Measuring and Mitigating Identity-Cue Preference Drift in LLM-based Recommender Systems
arXiv 2609.34229 · 2026-09-29SleuthBench：使用表格隐藏信号对统计LLM评估进行基准测试
SleuthBench: Benchmarking Statistical LLM Evaluation Using Tabular Hidden Signals
arXiv 2609.34228 · 2026-09-29何时选择取代提取？基于类型化决策模型的智能体记忆预注册测试
When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
arXiv 2609.34227 · 2026-09-29低延迟全球碳收支揭示2025年陆地碳汇强劲恢复
Low latency global carbon budget reveals strong land sink recovery in 2025
arXiv 2609.34226 · 2026-09-29USA：用于语言智能体跨域在线策略蒸馏的更新感知SAM
USA: Update-aware SAM for Cross-domain On-Policy Disitllation of Language Agents
arXiv 2609.34225 · 2026-09-29斜入射平行狭缝SPP场中的表面法向电自旋
Surface-Normal Electric Spin in Obliquely Excited Parallel-Slit SPP Fields
arXiv 2609.34224 · 2026-09-29揭示音视频大语言模型中的序数匹配偏差
Uncovering Ordinal-Matching Bias in Audio-Visual LLMs
arXiv 2609.34223 · 2026-09-29四足运动与人机交互中的本体感觉力估计
Proprioceptive Force Estimation for Quadruped Locomotion and Human-Robot Interaction
arXiv 2609.34222 · 2026-09-29银道面远侧脉泽源的三角视差
Trigonometric Parallaxes of Maser Sources toward the Far Side of the Milky Way
arXiv 2609.34219 · 2026-09-29基于自发语音的可解释且可泛化的LLM认知衰退检测
Explainable and Generalisable LLM-based Cognitive Decline Detection with Spontaneous Speech
arXiv 2609.34217 · 2026-09-29GAMF：用于阵列通用到达方向估计的学习与解析阵列传递函数匹配
GAMF: Learned and Analytical Array Transfer Function Matching for Array-Generic Direction-of-Arrival Estimation
arXiv 2609.34216 · 2026-09-29相同的胜者，不同的成功率：评估LLM智能体如何从失败中恢复
Same Winners, Different Success Rates: Evaluating How LLM Agents Recover from Failures
arXiv 2609.34215 · 2026-09-29GlyphBench：语言模型强化学习的游乐场
GlyphBench: A Playground for Language-Model Reinforcement Learning
arXiv 2609.34214 · 2026-09-29Rényi信道容量在非信号辅助信道模拟下的单调性
Monotonicity of the Rényi channel capacity under non-signaling assisted channel simulation
arXiv 2609.34213 · 2026-09-29X-MoD：超越混合深度（Mixture-of-Depths）的稀疏深度路由实用缩放定律
X-MoD: Practical Scaling Laws for Sparse-Depth Routing Beyond Mixture-of-Depths
arXiv 2609.34212 · 2026-09-29人类二尖瓣及经导管缘对缘修复的浸没几何流固耦合建模
Immersogeometric fluid-structure interaction modeling of the human mitral valve and transcatheter edge-to-edge repair
arXiv 2609.34209 · 2026-09-29年轻经典造父变星揭示的银河系大规模旋臂结构
Large-Scale Spiral Structure of the Milky Way Traced by Young Classical Cepheids
arXiv 2609.34208 · 2026-09-29用于幅度-相位表示学习的函数自编码器
Functional Autoencoders for Amplitude-Phase Representation Learning
arXiv 2609.34207 · 2026-09-29WorldGuide：在潜在世界模型中学习视觉-语言-动作策略的成功-失败边界
WorldGuide: Learning Success-Failure Boundaries in Latent World Models for Vision-Language-Action Policies
arXiv 2609.34206 · 2026-09-29通过求解器驱动的自我对弈学习优化
Learning to Optimize through Solver-Grounded Self-Play
arXiv 2609.34205 · 2026-09-29平面中临界 $p$-Laplace 方程的连续延拓、不存在性与 bubbling 现象
Unique continuation, nonexistence and bubbling for the critical $p$-Laplace equation in the plane
arXiv 2609.34204 · 2026-09-29拟细胞范畴与 Brauer 范畴的结构
Quasi-cellular categories and the structure of the Brauer category
arXiv 2609.34203 · 2026-09-29趋化-消耗系统中具有一般运动性的非恒定稳态的非线性稳定性
Nonlinear Stability of Nonconstant Steady States in Chemotaxis--Consumption Systems with General Motility
arXiv 2609.34202 · 2026-09-29利用超导量子比特对的动态失谐控制的等效$\Lambda$型系统中的量子存储器
Quantum memory in an effective $Λ$-type system using dynamic detuning control of a superconducting qubit pair
arXiv 2609.34201 · 2026-09-29Nakayama的量子拓扑斯约化与贝叶斯量子计算
Nakayama's reduction of quantum topos and Bayesian quantum computing
arXiv 2609.34200 · 2026-09-29正则单纯形张量：优化景观、猜想证明及其延伸
Regular simplex tensors: optimization landscape, conjecture proof, and beyond
arXiv 2609.34197 · 2026-09-29ConvCue：视觉语言模型的互补视觉归纳偏置
ConvCue: Complementary Visual Inductive Biases for Vision-Language Models
arXiv 2609.34196 · 2026-09-29PainterBench：用于工具使用语言模型的图形发散思维基准
PainterBench: A Figural Divergent-Thinking Benchmark for Tool-Using Language Models
arXiv 2609.34195 · 2026-09-29机器学习拉普拉斯级密度泛函：基于精确交换关联势与能量
Machine-learned Laplacian-level density functional from exact exchange-correlation potentials and energies
arXiv 2609.34194 · 2026-09-29
