这篇论文提出了IMNO,一个解决耗散PDEs的新方法,比传统神经网络操作符更稳定准确,特别适合对耗散系统的研究。
全部动态
This paper presents a new approach for timely risk classification with a focus on balancing key operating characteristics. It's a must-read for those interested in improving decision-making in clinical settings.
MetaCaster能从少量数据中训练出高效的轻量级时间序列预测器,对于资源有限的环境来说是个不错的选择,特别是与现有的轻量级预测器相比。
ProxyFormer模型在处理超长上下文和高分辨率生成方面表现出色,相较于传统模型,其压缩比高达64,训练序列长度可扩展至0.7M,值得一看。
This paper presents a novel approach to data attribution and error proxying for machine learning models in space missions, offering a more efficient and accurate way to assess model performance. It's a must-read for those interested in explainable AI and its applications in scientific research.
这篇论文提出了ChebBooster,一种基于切比雪夫多项式的训练免费外推框架,能显著提升扩散Transformer的推理效率,值得一看。
这篇论文深入探讨了量化投资系统的基本原理,提出了关于潜在规律、信息预算和系统架构的见解,对于对量化交易感兴趣的读者来说,是一篇值得阅读的论文。
Next-Scale Transformer模型在人脸合成方面表现出色,与现有模型结合,生成更精确的3D人脸模型,值得关注。
想了解如何用 XGBoost 构建投资组合?KellyBoost 模型值得一试,它提供了精确的成长最优分配方法。
This research offers a significant advancement in privacy-enhancing instance encoding, providing stronger theoretical guarantees and broader applicability. It's a must-read for those interested in data privacy and encoding techniques.
This study presents a novel BP monitoring method using deep learning and physics constraints, offering improved accuracy and robustness compared to traditional methods. It's a must-read for those interested in contactless BP monitoring and deep learning applications in healthcare.
Prime Agent 是一个强大的开源 harness,它通过递归语言模型和持续 harness 提高了长期评估和编码代理工作流程的效率,其性能在多个任务上超过了其他 harness,值得一试。
EarthVerse基准测试为评估科学智能体提供了全面的方法,揭示了当前智能体在跨证据和尺度上的不足,值得专业人士关注。
INDI significantly enhances VLA models, outperforming GR00T-N1.7 by 20.4% on SimplerEnv-Bridge and 6.2% on RoboCasa Kitchen, making it a notable improvement over traditional behavior cloning approaches.
This paper offers a new perspective on the consistency of retrieval-augmented QA systems, highlighting the importance of the Snapshot Compatibility Audit method. It's a must-read for those interested in QA system reliability and the nuances of corpus-induced changes.
CacheRouter通过双路径设计优化了LLM系统中的工具使用,自动化工具注册和运行时更新,显著提高缓存命中率,降低输入成本,值得一试。
This research provides a new approach to improve the reliability of LLMs in decision-making by calibrating claim-level confidence, which is particularly useful for high-stakes domains where accurate uncertainty estimation is crucial.
SchemaGUI提供了一个新的基准,用于评估可控制GUI生成,特别是对于LLMs在几何空间控制和布局复杂性方面的表现进行了深入分析,对于想要了解GUI生成领域最新进展的人来说是个好资源。
仅展示最近 2000 条内容,更早的内容请查阅 AI 日报存档