0

GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs

GeoStack is a modular framework that composes domain experts in Vision-Language Models while preserving foundational knowledge and enabling constant-time inference through geometric constraints on adapter manifolds.

Year
2026
Venue
arXiv 2026
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2605.06477ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

We address the challenge of knowledge composition in Vision-Language Models (VLMs), where accumulating expertise across multiple domains or tasks typically leads to catastrophic forgetting. We introduce GeoStack (Geometric Stacking), a modular framework that allows independently trained domain experts to be composed into a unified model. By imposing geometric and structural constraints on the adapter manifold, GeoStack ensures the foundational knowledge of the base model is preserved. Furthermore, we mathematically demonstrate a weight-folding property that achieves constant-time inference complexity (O(1)), regardless of the number of integrated experts. Experimental results across multi-domain adaptation and class-incremental learning show that GeoStack provides an efficient mechanism for long-term knowledge composition while significantly mitigating catastrophic forgetting. Code is available at https://github.com/QuantitativeImagingLaboratory/GeoStack.

Authors

2