2026-09论文中文摘要
超越端到端黑箱映射：面向认知驱动面部反应生成的意图体框架
Beyond End-to-End Black Box Mapping: An Intentional Agent Framework for Cognitive-driven Facial Reaction Generation
arXiv 2609.34419 · 2026-09-29OSPD：用于人格一致对话的在线策略自蒸馏
OSPD: On-Policy Self-Distillation for Persona-Consistent Dialogue
arXiv 2609.34418 · 2026-09-29太阳孪生星/相似星周围的行星（PASTA）III：含行星太阳相似星中的化学时钟关系
Planets Around Solar Twins/Analogs (PASTA) III: Chemical Clock Relations in Planet-Hosting Solar Analogs
arXiv 2609.34417 · 2026-09-29受限手性模式的激发间隙度量临界零点涨落
Excitation Gap of a Confined Chiral Mode Measures Critical Zero-Point Fluctuations
arXiv 2609.34416 · 2026-09-29PROACT-Agent：用于实时安全的渐进式运行时监督与主动断路
PROACT-Agent: Progressive Runtime Oversight and Active Circuit-breaking for Real-Time Safety
arXiv 2609.34415 · 2026-09-29从世界模型到世界行动模型：重新思考下一状态预测
From World Models to World Action Models: Rethinking Next-State Prediction
arXiv 2609.34414 · 2026-09-29排列异或的量子安全性：基于傅里叶分析
Quantum Security of XOR of Permutations via Fourier Analysis
arXiv 2609.34413 · 2026-09-29从语言到任务映射：在保留任务相关自由度的同时编译语义关系
From Language to Task Maps: Compiling Semantic Relations While Preserving Task-Relevant Freedom
arXiv 2609.34412 · 2026-09-29人类认知的数学及其应用：问题求解瓶颈的资源理性搜索
Mathematics for and by human cognition: A resource-rational search for bottlenecks in problem-solving
arXiv 2609.34410 · 2026-09-29将视觉推理蒸馏到文本空间
Distilling Visual Reasoning into Text Space
arXiv 2609.34408 · 2026-09-29超越文本思维链：面向大型音频语言模型的JEPA条件潜在推理
Beyond Textual Chain-of-Thought: JEPA-Conditioned Latent Reasoning for Large Audio Language Models
arXiv 2609.34407 · 2026-09-29解锁少步扩散以实现忠实预览
Unlocking Few-Step Diffusion for Faithful Previews
arXiv 2609.34406 · 2026-09-29核心坍缩超新星引力波：对前身星、旋转速率和核态方程的依赖
Gravitational Waves from Core-Collapse Supernovae: Dependence on the Progenitor Star, Rotation Rate and Nuclear Equation of State
arXiv 2609.34405 · 2026-09-29Eval4DiRec：基于扩散的推荐系统的统一与系统性评估框架
Eval4DiRec: A Unified and Systematic Evaluation Framework for Diffusion-based Recommender Systems
arXiv 2609.34404 · 2026-09-29连续统费米子动力学的不连续性
Discontinuity of Continuum Fermion Dynamics
arXiv 2609.34402 · 2026-09-29黑洞环衰减中耦合场的避免交叉与共振：爱因斯坦-麦克斯韦-轴子系统案例研究
Avoided crossings and resonances in black hole ringdown with coupled fields: A case study of the Einstein-Maxwell-axion system
arXiv 2609.34401 · 2026-09-29接触感知阻抗控制器用于机器人辅助超声成像
Contact-Aware Impedance Controller for Robot-Assisted Ultrasound Imaging
arXiv 2609.34400 · 2026-09-29CoRF：通过学习传播并保持阵列物理特性的跨场景射频合成
CoRF: Cross-Scene RF Synthesis by Learning Propagation and Preserving Array Physics
arXiv 2609.34399 · 2026-09-29GeoCFM：用于矿产赋存采样的仅正例条件流匹配
GeoCFM: Positive-Only Conditional Flow Matching for Mineral Occurrence Sampling
arXiv 2609.34398 · 2026-09-29SkillFocus：通过能力分解演化智能体技能
SkillFocus: Evolving Agent Skills via Capability Decomposition
arXiv 2609.34397 · 2026-09-29HyperDAM：用于SAM 3跟踪的具有非模态扩展的高光谱干扰物感知记忆
HyperDAM: Hyperspectral Distractor-Aware Memory with Amodal Expansion for SAM 3 Tracking
arXiv 2609.34396 · 2026-09-29环到其典范模的嵌入
On embeddings of rings into their canonical modules
arXiv 2609.34395 · 2026-09-29单节点网络关键性中的目标转移：最优常数与精确分离阈值
Objective Transfer in Single-Node Network Criticality: Optimal Constants and Exact Separation Thresholds
arXiv 2609.34394 · 2026-09-29多长度跨模态哈希检索的尺度可分解分数阶扩散相关性分辨率迁移
Relevance-Resolution Transfer via Scale-Decomposable Fractional Diffusion for Multi-Length Cross-Modal Hash Retrieval
arXiv 2609.34393 · 2026-09-29Org-Agent：超越个人助理，迈向组织智能体
Org-Agent: Beyond Personal Assistants Towards Organizational Agents
arXiv 2609.34392 · 2026-09-29P2P：用于未配对单细胞扰动响应预测的跨视图群体去噪
P2P: Cross-View Population Denoising for Unpaired Single-Cell Perturbation Response Prediction
arXiv 2609.34391 · 2026-09-29互惠引导：编排草稿与验证预算以推进扩散-自回归自推测前沿
Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier
arXiv 2609.34388 · 2026-09-29选择之前先观察：重新思考在线策略蒸馏中的词汇稀疏化
Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation
arXiv 2609.34386 · 2026-09-29即时代理记忆与运行时代理研究
Just-In-Time Agent Memory with Runtime Agentic Research
arXiv 2609.34385 · 2026-09-29RoboIRGBench：视觉-语言-动作模型中的隐式指代接地基准
RoboIRGBench: Benchmarking Implicit Referential Grounding in Vision-Language-Action Models
arXiv 2609.34384 · 2026-09-29纠正以预测：多模态属性值提取的伪值纠正
Correcting to Predict: Pseudo-Value Correction for Multimodal Attribute Value Extraction
arXiv 2609.34383 · 2026-09-29拆分拟阵行列式
Splitting the Matroid Determinant
arXiv 2609.34382 · 2026-09-29联合与跨模态视频-音频生成及编辑：统一公式与设计分类法
Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy
arXiv 2609.34381 · 2026-09-29DPS：基于半统一内存的双精度LLM服务系统
DPS: Dual-Mode Precision LLM Serving with Semi-Unified Memory
arXiv 2609.34380 · 2026-09-29无导数广义多变量超螺旋控制用于受约束的欧拉-拉格朗日系统
Derivative-Free Generalized Multivariable Super-Twisting Control for Constrained Euler-Lagrange Systems
arXiv 2609.34379 · 2026-09-29Marathoner：超长时域自主智能
Marathoner: Ultra-Long-Horizon Autonomous Intelligence
arXiv 2609.34378 · 2026-09-29Takagi函数的正测度与水平集
Positive measure and level sets of the Takagi function
arXiv 2609.34377 · 2026-09-29在智能体行动之前：面向分布式系统中证据获取的保障感知语义调度
Before Agents Act: Assurance-Aware Semantic Scheduling for Evidence Acquisition in Distributed Systems
arXiv 2609.34376 · 2026-09-29LRC-JEPA：解耦动力学与残差上下文以构建高效世界模型
LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models
arXiv 2609.34375 · 2026-09-29ABC-Align：具有自适应偏差控制的预测驱动对齐
ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
arXiv 2609.34374 · 2026-09-29PersMem：将个性内化到LLM代理的双路径记忆中
PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents
arXiv 2609.34372 · 2026-09-29从静态到动态：从图像到视频扩散模型的策略内蒸馏
From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Models
arXiv 2609.34371 · 2026-09-29Spexis：面向LLM推理的投机性前瞻调度
Spexis: Speculative Lookahead Scheduling for LLM Inference
arXiv 2609.34370 · 2026-09-29速度的形状：分布式量子电路模拟中分区几何形状与秩密度的影响
The Shape of Speed: Impacts of Partition Geometry and Rank Density in Distributed Quantum Circuit Simulations
arXiv 2609.34369 · 2026-09-29黏性系数的一个临界值：在伪抛物型Fisher-KPP方程中触发振荡行波
A Critical Value for the Viscosity Coefficient: Triggering Oscillatory Traveling Waves in the Pseudo-parabolic Fisher-KPP Equation
arXiv 2609.34368 · 2026-09-29当驾驭胜过规模，以及当阅读胜过两者
When Harness Beats Scale, and When Reading Beats Both
arXiv 2609.34366 · 2026-09-29腔磁振子学与布拉格和反布拉格镜中的连续谱束缚态
Cavity magnonics and bound states in the continuum with Bragg and anti-Bragg mirrors
arXiv 2609.34365 · 2026-09-29$\eta_t \to HZ$ 的次次领头阶 QCD 修正
Next-to-Next-to-Leading Order QCD Corrections to $η_t \to HZ$
arXiv 2609.34364 · 2026-09-29SyncRA：在全模态模型中学习时间对应关系
SyncRA: Learning Temporal Correspondence in Omni-Modal Models
arXiv 2609.34363 · 2026-09-29FutureDuet：在世界动作模型中将观测访问与未来监督解耦
FutureDuet: Decoupling Observation Access from Future Supervision in World Action Models
arXiv 2609.34362 · 2026-09-29
