English

Attention in Geometry: Scalable Spatial Modeling via Adaptive Density Fields and FAISS-Accelerated Kernels

Machine Learning 2026-02-03 v2 Computer Vision and Pattern Recognition Graphics

Abstract

This work introduces Adaptive Density Fields (ADF), a geometric attention framework that formulates spatial aggregation as a query-conditioned, metric-induced attention operator in continuous space. By reinterpreting spatial influence as geometry-preserving attention grounded in physical distance, ADF bridges concepts from adaptive kernel methods and attention mechanisms. Scalability is achieved via FAISS-accelerated inverted file indices, treating approximate nearest-neighbor search as an intrinsic component of the attention mechanism. We demonstrate the framework through a case study on aircraft trajectory analysis in the Chengdu region, extracting trajectory-conditioned Zones of Influence (ZOI) to reveal recurrent airspace structures and localized deviations.

Keywords

Cite

@article{arxiv.2601.06135,
  title  = {Attention in Geometry: Scalable Spatial Modeling via Adaptive Density Fields and FAISS-Accelerated Kernels},
  author = {Zhaowen Fan},
  journal= {arXiv preprint arXiv:2601.06135},
  year   = {2026}
}

Comments

Indepented Study. 31 pages, 3 figures. Includes full mathematical derivation of Adaptive Density Fields (ADF), implementation of FAISS-accelerated kernels, and a physics-informed trajectory POI detection pipeline

R2 v1 2026-07-01T08:58:15.602Z