Koopman算子遇上小波变换，为非线性动力学分析提供新框架
arXiv:2605.14224v1 Announce Type: cross Abstract: We present an in-depth analysis of the Koopman semigroup via wavelet transform. Towards this goal, w…
动态分辨率扩散模型降低图像修复计算开销，避免重复编解码，实现高效恢复。
arXiv:2605.14267v1 Announce Type: cross Abstract: Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. Howeve…
最新研究挑战ReAct默认架构，提出Web Agent应转向先规划后执行的范式，直击大模型智能体核心设计。
arXiv:2605.14290v1 Announce Type: cross Abstract: ReAct has become the default architecture across LLM agents, and many existing web agents follow thi…
用矩阵空间抽象局部转移几何，强化学习实现组合泛化新范式。
arXiv:2605.14304v1 Announce Type: cross Abstract: Compositional generalization in sequential decision-making requires identifying which parts of prior…
提出模拟RF计算新范式，突破传统数字计算瓶颈，实现MU-MIMO系统下极致能效的边缘AI推理。
arXiv:2605.14331v1 Announce Type: cross Abstract: Modern edge devices increasingly rely on neural networks for intelligent applications. However, conv…
几何引导的隐藏状态替换，揭秘扩散模型在语言模型中的最佳插入位置，DiHAL创新方案提升性能。
arXiv:2605.14368v1 Announce Type: cross Abstract: Continuous diffusion language models lag behind autoregressive transformers, partly because diffusio…
论文提出最优模式检测树，以可解释的符号规则实现透明化分类，挑战黑盒模型
arXiv:2605.14374v1 Announce Type: cross Abstract: Pattern discovery in data plays a crucial role across diverse domains, including healthcare, risk as…
无需额外训练，通过进化合并大模型权重即可提升推理性能——前沿的免训练规模扩展方法。
arXiv:2605.14386v1 Announce Type: cross Abstract: We present Darwin Family, a framework for training-free evolutionary merging of large language model…
四足机器人用柔性脚替代刚硬脚，吸收冲击并存储弹性能，实现更高能效的运动。
arXiv:2605.14411v1 Announce Type: cross Abstract: Quadruped robots are often designed with rigid feet to simplify control and maintain stable contact …
全新基准测试聚焦代码智能体在连续软件包版本升级中的能力，比单次任务更贴近真实维护场景。
arXiv:2605.14415v1 Announce Type: cross Abstract: Coding agents powered by large language models are increasingly expected to perform realistic softwa…
联邦强化学习新突破：单时间尺度actor-critic框架平衡协作与个性化，适合多智能体异构环境。
arXiv:2605.14423v1 Announce Type: cross Abstract: Despite the popularity of the actor-critic method and the practical needs of collaborative policy tr…
电商搜索新范式，生成式检索结合语义聚类ID与专家引导强化学习，实现端到端高效检索
arXiv:2605.14434v1 Announce Type: cross Abstract: Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval…
视觉物体移除评估新基准，解决感知一致性难题，比现有指标更贴近人类判断。
arXiv:2605.14534v1 Announce Type: cross Abstract: Evaluating object removal in images and videos remains challenging because the task is inherently on…
AI agent自主设计成分描述符，实现材料科学属性预测的自动化研究新范式
arXiv:2605.14671v1 Announce Type: cross Abstract: Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent propos…
结合视觉核心引导与对比学习，攻克多模态中风预后预测的平衡难题。
arXiv:2605.14710v1 Announce Type: cross Abstract: Deep learning and multi-modal fusion have demonstrated transformative potential in medical diagnosis…
提出短视意图模型IntentVLA，解决机器人模仿数据多模态歧义问题，提升操作准确性
arXiv:2605.14712v1 Announce Type: cross Abstract: Robot imitation data are often multimodal: similar visual-language observations may be followed by d…
用认知不确定性引导知识蒸馏，解决学生误解分类中数据稀疏与边界模糊难题。
arXiv:2605.14752v1 Announce Type: cross Abstract: Accurately identifying student misconceptions is crucial for personalized education but faces three …
探讨组合稀疏性作为神经网络架构设计的归纳偏置，从理论上破解高维学习中的维度灾难。
arXiv:2605.14764v1 Announce Type: cross Abstract: Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of d…
论文提出即插即用的振荡式数据体积调度方法，超越传统样本选择，显著提升模型训练效率。
arXiv:2605.14773v1 Announce Type: cross Abstract: Data selection accelerates training by identifying representative training data while preserving mod…
闭环验证推理突破复杂视觉生成，用可验证的多步推理解决规划幻觉问题，效果惊艳。
arXiv:2605.14876v1 Announce Type: cross Abstract: Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step g…