arXiv 2609.34715 · cs.AI · 2026-09-28
PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs
Zhentao Tan, Jianrong Zhang, Ruijie Quan, Yi Yang
Zhejiang University
在最新榜 #247 本站收录于 2026-10-21
一句话要点
PDE-JEPA 用预测式表示预训练学习参数化偏微分方程的潜在动力学，替代重建式目标。
PDE-JEPA learns latent dynamics of parametric PDEs with predictive (JEPA-style) pretraining instead of reconstruction.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：AI for Science
- Scaling Parameter-Efficient Fine-Tuning for Brain Encoding ▲244
- EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery ▲112
- Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts ▲103
- From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research ▲54
- Does Learning Protein Folding Generalize to Broader Reasoning? ▲51
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-23。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。