ScaleAware-JEPA: Latent Representation for Discovery in Multiscale Physical Fields
- Published
- Source
- arXiv
- Paper number
- 523
- Field
- Machine Learning
- arXiv ID
- 2606.29723
Key points
- Constrained Diffusion Decomposition, or CDD, decomposes fields into pixel-level scale components.
- The CDD scale determines the masking geometry, aligning the physical scale hierarchy with the prediction task.
- It is applied to three heterogeneous domains: MHD turbulence, the NGC 3627 molecular gas field, and Chengdu night lights.
- It can generate a dense latent atlas without labels, segmentation, or catalogs.
- It quantitatively verifies the superiority of scale-aware masking over fixed patch masks.
- It is an independent study performed on consumer hardware, specifically an Apple M3 Pro and an RTX 3090.
Paper links
External research summaries. These are not HDATF publications or measured product results.