2026-08论文中文摘要
强化深度感知哈希以抵御规避攻击且无需重新训练
Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining
arXiv 2608.03101 · 2026-08-05面向动作识别的基于自适应样本生成的通道级动态知识蒸馏
Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition
arXiv 2608.03100 · 2026-08-05语言的作用与证据支持：具身智能体中语言接地的功能角色分类与证据审查
What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents
arXiv 2608.03099 · 2026-08-05锂作为LAMOST中分辨率巡天中致密天体双星候选体的指示标
Lithium as a Signpost for Compact Object Binary Candidates in the LAMOST Medium Resolution Survey
arXiv 2608.03098 · 2026-08-05有限域F_p上的Vieta图计数
Counting in Vieta graphs over $\mathbb{F}_p$
arXiv 2608.03097 · 2026-08-05FakeI2V-Bench：评估图像级深度伪造检测器在深度伪造视频检测中的适用性
FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection
arXiv 2608.03096 · 2026-08-05VIVID：面向越南NLP中比喻语言差距的文化基准测试集
VIVID: A Culturally Grounded Benchmark Exposing the Figurative Language Gap in Vietnamese NLP
arXiv 2608.03095 · 2026-08-05HIP 61637 b：一颗围绕大质量A型恒星运行的近圆轨道褐矮星，由TESS发现
HIP 61637 b: a TESS Brown Dwarf in a Near-circular Orbit around a Massive A-type Star
arXiv 2608.03094 · 2026-08-05DHMark：基于Diffie-Hellman引导拒绝采样的LLM生成文本公钥水印
DHMark: Public-Key Watermarking for LLM-Generated Text via Diffie-Hellman-Guided Rejection Sampling
arXiv 2608.03093 · 2026-08-05位置偏差破坏基于大语言模型的列表式重排序中的偏好一致性
Position Bias Undermines Preference Consistency in Listwise LLM-Based Reranking
arXiv 2608.03091 · 2026-08-05六方氮化硼（hBN）中量子发射体的自旋与光学性质的关联
Correlating spin and optical properties of quantum emitters in hBN
arXiv 2608.03090 · 2026-08-05面向大语言模型预训练的可扩展、感知频率与长度的子文档去重
Scalable Frequency- and Length-Aware Subdocument Deduplication for Large Language Model Pretraining
arXiv 2608.03089 · 2026-08-05遍历马尔可夫过程拟合优度的新方法
A New Approach to Goodness of Fit for Ergodic Markov Processes
arXiv 2608.03088 · 2026-08-05SynEnergy：面向合成能源数据生成的异常语义引导扩散模型
SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data Generation
arXiv 2608.03087 · 2026-08-05基于物理引导深度学习模型加速的患者特异性微波消融自动规划
Automatic Patient-Specific Microwave Ablation Planning Accelerated by a Physics-Guided Deep Learning Model
arXiv 2608.03086 · 2026-08-05非结构化结果的因果推断
Causal Inference with Unstructured Outcomes
arXiv 2608.03085 · 2026-08-05SUV：将未来场景理解建模为视频生成的端到端驾驶
SUV: Future Scene Understanding as Video Generation for End-to-End Driving
arXiv 2608.03084 · 2026-08-05GSTEP：面向高效视频大语言模型的全局时空密度驱动视觉令牌剪枝
GSTEP: Global Spatio-Temporal Density-Driven Visual Token Pruning for Efficient Video Large Language Models
arXiv 2608.03083 · 2026-08-05DiverseDiT++：量化、分析与提升扩散Transformer的表示多样性
DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers
arXiv 2608.03082 · 2026-08-05Lipschitz上置信界的收敛性证明
A Proof of the Convergence a Lipschitz Upper Confidence Bound
arXiv 2608.03081 · 2026-08-05网络自动化中的前沿大语言模型陷阱
The Frontier LLM Trap in Network Automation
arXiv 2608.03080 · 2026-08-05LDU-Bench：面向不同布局电路背景下光刻缺陷理解的多模态大语言模型评估基准
LDU-Bench: Multimodal LLM Evaluation for Lithography Defect Understanding under Layout-Varying Circuit Backgrounds
arXiv 2608.03078 · 2026-08-05PAMT：面向多领域机器翻译的过程对齐强化学习
PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translation
arXiv 2608.03077 · 2026-08-05智能体经济学：在 minimal 外部条件下，AI 智能体间能否涌现出自发的经济行为？
AI Agent Economics: Can Autonomous Economic Behavior Emerge among AI Agents under Minimal External Conditions?
arXiv 2608.03076 · 2026-08-05最优传输歧义集下基于神谕的分布鲁棒优化
Oracle-Based Distributionally Robust Optimization under Optimal Transport Ambiguity Sets
arXiv 2608.03075 · 2026-08-05用于跨音速风洞试验的增材与减材复合制造柔性机翼模型的构建
Construction of flexible wing models by combined manufacturing of additive and subtractive processes for transonic wind tunnel testing
arXiv 2608.03074 · 2026-08-05NbSe2薄片中压力诱导的无磁场超导二极管效应
Pressure induced magnetic-field-free superconducting diode effect in NbSe2 flake
arXiv 2608.03072 · 2026-08-05参数优化：面向大语言模型工具调用的难度分级基准与探测引导训练
Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls
arXiv 2608.03071 · 2026-08-05在Q学习中不确定性下的TD目标聚合再探讨
Revisiting TD Target Aggregation under Uncertainty in Q-Learning
arXiv 2608.03069 · 2026-08-05CVPO：通过值方差自适应与动态课程学习增强大语言模型的强化学习推理能力
CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning
arXiv 2608.03068 · 2026-08-05一类Vaidya时空上Hawking辐射的Fredenhagen-Haag推导的推广
A generalization of the Fredenhagen-Haag derivation of Hawking radiation for a class of Vaidya space-times
arXiv 2608.03066 · 2026-08-05基于解析器栈分类的高效语法约束解码
Efficient Grammar-Constrained Decoding via Parser Stack Classification
arXiv 2608.03065 · 2026-08-05基于全局图验证的VLM驱动3D室内场景生成优化
Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation
arXiv 2608.03064 · 2026-08-05SeqLLM：为高风险决策场景下的微信支付增强序列大语言模型（LLM）的行为序列建模能力
SeqLLM: Augmenting LLMs with Behavioral-Sequence Modeling for High-Stakes Decisions at WeChat Pay
arXiv 2608.03063 · 2026-08-05TraceCAD：面向智能体CAD生成的轨迹引导修复
TraceCAD: Trace-Guided Repair for Agentic CAD Generation
arXiv 2608.03062 · 2026-08-05异构信息网络中可扩展的精确稠密P部子图搜索
Scalable Exact Densest P-Partite Subgraph Search in Heterogeneous Information Networks
arXiv 2608.03061 · 2026-08-05地月交会与接近操作的被动安全凸制导
Passively Safe Convex Guidance for Cislunar Rendezvous and Proximity Operations
arXiv 2608.03060 · 2026-08-05RIDGE：用于图像编辑的基于内部动态引导的重加噪方法
RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editing
arXiv 2608.03059 · 2026-08-05压力诱导热电半导体Mg3Sb2中的超导性
Pressure-induced Superconductivity in Thermoelectric Semiconductor Mg3Sb2
arXiv 2608.03058 · 2026-08-05TASQ：用于扩散模型的时间自适应比特稀疏化量化
TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models
arXiv 2608.03057 · 2026-08-05原子阵列中最亚辐射态的 heralded 自由电子写入
Heralded Free-Electron Writing of the Most Subradiant State in an Atomic Array
arXiv 2608.03056 · 2026-08-05PDD-RRG：面向研究级放射学报告生成的后验诊断决策
PDD-RRG: Posterior Diagnostic Decision for Study-level Radiology Report Generation
arXiv 2608.03055 · 2026-08-05迈向更具表达力的口语大语言模型：细粒度意图基准测试与音-词解耦策略优化
Towards More Expressive Spoken LLMs: Fine-Grained Intent Benchmarking and Acoustic-Lexical Decoupled Policy Optimization
arXiv 2608.03054 · 2026-08-05含各向异性的电阻抗断层成像的稳定性及其在深度卡尔德隆方法中的应用
Stability of Electrical Impedance Tomography with Anisotropies and its Application to the Deep Caldeón Method
arXiv 2608.03053 · 2026-08-05视觉-语言-动作（VLA）模型应如何使用本体感受状态？
How Should Vision-Language-Action Models Use Proprioceptive State?
arXiv 2608.03052 · 2026-08-05CUDA MPC：一款面向模型预测控制的GPU原生求解器
CUDA MPC: A GPU-Native Solver for Model Predictive Control
arXiv 2608.03051 · 2026-08-05通过跨模态自举学习音乐风格以实现钢琴编曲
Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping
arXiv 2608.03050 · 2026-08-05双层激子凝聚体中的隐藏量子几何
Hidden Quantum Geometry in Bilayer Exciton Condensates
arXiv 2608.03049 · 2026-08-05PI-Mem：通过并行迭代式记忆将长上下文推理推向360万 tokens
PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory
arXiv 2608.03048 · 2026-08-05AIDE：基于提炼专业知识的自动化指令，用于无参考的运动技能指导
AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching
arXiv 2608.03047 · 2026-08-05
