jNO让神经算子与基础模型训练更高效，支持数据与物理双重驱动。
jNO: A JAX Library for Neural Operator and Foundation Model Training
- 统一符号语言编译优化管道，实现模型、残差、损失一体化
- 支持无重构切换算子回归、网格感知残差与PDE约束训练
- 适合需要物理信息融合的科学计算与模型调优的研究者
jNO（JAX神经算子）是一个原生JAX的神经算子与基础模型训练库，统一支持数据驱动和物理信息驱动的训练。其核心设计为一种追踪系统，将域、模型调用、残差、监督损失与诊断信息以同一符号语言书写，并编译为单一优化流程。用户可在算子回归、网格感知残差评估与PDE约束训练间无缝切换，无需重构代码。jNO还支持多模型组合、参数级细粒度控制（模型、优化器、学习率）、超参数调优，以及针对已翻译偏微分方程（PDE）基础模型家族的原生JAX工作流。源码仓库地址：https://github.com/FhG-IISB/jNO。
原文摘要 · Abstract (English)
jNO (jax Neural Operators) is a JAX-native library for neural operators and foundation models with unified support for both data-driven and physics-informed training. Its core design is a tracing system in which domains, model calls, residuals, supervised losses, and diagnostics are written in one symbolic language and compiled into one optimization pipeline. This allows users to move between operator regression, mesh-aware residual evaluation, and PDE-constrained training without restructuring the surrounding code. jNO also supports multi-model compositions, fine-grained control at parameter level (model, optimizer, and learning rate), hyperparameter tuning, and JAX-native workflows for translated PDE foundation-model families. The source repository is available at https://github.com/FhG-IISB/jNO.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。