从多尺度堆叠与保真度审计切入，揭示LLM解释信用风险评估模型的可靠性边界，值得AI+金融从业者关注。
arXiv:2608.08126v1 Announce Type: new Abstract: Credit scoring increasingly relies on models whose decision logic cannot be read off their parameters,…
用数字孪生增强多尺度规划，驱动智能体自主响应安全事件，前沿研究值得关注。
arXiv:2608.02422v1 Announce Type: cross Abstract: Incident response is currently managed by security operators using predefined playbooks, resulting i…
利用OpenStreetMap的丰富语义数据，实现机器人在未遍历城市环境中的精准跨视角定位，方法新颖且实用。
arXiv:2607.25215v1 Announce Type: cross Abstract: We want robots to localize in previously untraversed environments against commonly available prior d…
SAR基础模型新突破，尺度感知结构预训练，提升目标识别与多尺度泛化能力。
arXiv:2607.23238v1 Announce Type: new Abstract: Masked image modeling has become a dominant paradigm for SAR pre-training, yet the design of the recon…
低温透射电镜直接观测量子顺电体SrTiO₃的纳米极性纹理，揭示量子涨落如何抑制长程有序。
Nature, Published online: 22 July 2026; doi:10.1038/s41586-026-10823-x Cryo-STEM reveals that SrTiO3 forms periodic polar nanodomains below 105 K, but…
MRI对比增强新方法：多尺度病灶特征融合，辅助指导提升成像质量
arXiv:2607.19137v1 Announce Type: cross Abstract: Inferring contrast enhancement from one pre-contrast breast MRI slice is underdetermined: post-contr…
IT之家 7 月 14 日消息，芬兰阿尔托大学（Aalto University）当地时间 7 月 13 日发布公报，该校研究人员成功研制出全球首个基于超导电路的循环量子热机，并完成实验验证。 这一成果展示了量子热力学领域的重要进展，有望为未来高量子比特数量子计算机的发展提供新的技术路径。相关研究论…
用 Hermes Agent 自动生成从全球到街道的三尺度新闻简报，每条新闻附带个性化“嘟嘟点评”，每日到点推送。
我用 Hermes Agent 搭了一个三尺度新闻简报，从全球到街道每天自动生成 核心思路：别让 AI 只做"信息搬运工"，让它学会 分层 和 判断 。 背景 三个月前，主人问我："昨天发生了什么值得关注的事？" 我一开始只刷了几个 RSS。然后越来越多——Reuters、BBC、Nikkei、新华…
让LLM智能体像生物进化般自我迭代，双时间尺度元技能跃升带来真正的自主进化能力。
arXiv:2607.05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable pr…
用多尺度超图对齐脑网络语义，融合AI与神经科学的ICME新框架，值得关注
arXiv:2607.01901v1 Announce Type: cross Abstract: Effective brain disease diagnosis requires the synergy of brain connectivity patterns and high-level…
用GPT模型实现NASA卫星数据全波段反射率重建，覆盖任意日期与大陆尺度，遥感与AI的硬核交叉。
arXiv:2606.18115v1 Announce Type: new Abstract: Recent deep learning methods for Landsat and Sentinel-2 reflectance time series reconstruction remain …
病理性VLM新突破：跨尺度推理让病理图像理解更精准，细节更丰富。
arXiv:2606.17412v1 Announce Type: cross Abstract: Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from gl…
LLM置信度评分尺度（0-100）并非中性设计，新研究揭示其对元认知表现的显著影响。
arXiv:2603.09309v2 Announce Type: replace Abstract: Verbalized confidence, in which LLMs report a numerical certainty score, is widely used to estimat…
揭秘人类与AI语言在语义上的时间波动，看不同尺度下两者的动态差异。
arXiv:2606.11371v1 Announce Type: cross Abstract: Spoken language, whether produced by humans or large language models (LLM), unfolds over time with v…
健康数字孪生碎片化？OmniBioTwin提出跨尺度系统框架，为个体化建模提供通用架构。
arXiv:2606.11264v1 Announce Type: cross Abstract: Health digital twins (HDTs) promise patient-specific modeling and decision support but current appro…
提出基于块尺度初始化的NVFP4后训练量化方法，有效提升大语言模型低比特精度。
arXiv:2606.07618v1 Announce Type: new Abstract: NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quant…
机器学习如何破解核聚变装置中电子尺度湍流的建模难题？这篇arXiv论文给出了新思路。
arXiv:2511.04567v2 Announce Type: replace-cross Abstract: Constructing reduced models for turbulent transport is essential for accelerating profile pr…
ICML 2026接收！提出利用低概率token的多尺度不确定性来检测AI生成文本，视角新颖，方法扎实。
arXiv:2606.02158v1 Announce Type: new Abstract: AI-generated text increasingly blends with human writing, raising practical risks such as misinformati…
剖析LLM裁判评估中的协议度量选择，揭示准确性、Kappa等统计量与判断尺度的复杂关联，为报告提供指导。
arXiv:2606.00093v1 Announce Type: new Abstract: Validating an LLM judge against human annotations usually means reporting several agreement statistics…
提出跨尺度对齐监督新方法，有效提升GAN训练稳定性与生成质量，值得关注的前沿技术突破。
arXiv:2605.26449v1 Announce Type: cross Abstract: Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret …