The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders
Different vision neural networks -- trained to classify, contrast, reconstruct, or match images to text -- should have correspondingly different internal representations. We report that they do not. After training, the top sixteen principal directions of variation inside thirteen modern vision encoders converge to the same sixteen-dimensional geometric object. We call this the cross-architecture substrate and study it with PCA, centred kernel alignment (CKA), and Pang 2026 calibration. The substrate transports across four visual domains (natural photographs, medical CT, satellite, microscopy) at median Procrustes-CKA 0.679, and across eight domains (adding sketches, depth, thermal infrared, astronomy) at 0.604, every pair >0.40. It survives Pang calibration globally (7.4x disc-vs-MAE separation, n=13,394) and locally (4.82-5.30, p<10^{-44}). It is not pixel statistics (0.263), not Gabor features (0.31), not a random projection (0.041), and emerges in the first 10% of training while accuracy keeps climbing. We deliver four applications: a label-free transferability filter beating LogME (3x faster, +0.15 Kendall-tau); a four-way domain detector (99.6% accuracy); a frozen low-shot probe (16 dims beat 768-dim DINOv2 by 3.78pp at N=50 labels per class); and a teacher-free distillation auxiliary matching trained-teacher KD on 33 pairs (7.56pp peak gain at 10% label fraction). The substrate does not cross modalities, does not help cross-paradigm distillation, and does not predict transfer quality (rho=0.08 against transfer accuracy).
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Domain-Contextualized Inference: A Computable Graph Architecture for Explicit-Domain Reasoning
We establish a computation-substrate-agnostic inference architecture in which domain is an explicit first-class computational parameter. This produces domain-scoped pruning that reduces per-query search space from O(N) t…
$π$-RAG: Oblivious Retrieval via Semantic Quantization and Transcendental Addressing for Large Language Models
This paper introduces $π$-RAG, a novel architecture for oblivious retrieval that decouples Large Language Models (LLMs) from sensitive data storage without sacrificing semantic understanding. Traditional Retrieval-Augmen…
Saturating Scaling Laws for Equational Discovery: A Phenomenology of Growth Dynamics in Three Toy Substrates with Two Real-World Replications
We investigate growth dynamics in deterministic equational discovery substrates. Across three toy domains (arithmetic, boolean, higher-order list; n=592 trajectories), short-range substrate sizes fit a power-law N(t) pro…
TransPimLib: A Library for Efficient Transcendental Functions on Processing-in-Memory Systems
Processing-in-memory (PIM) promises to alleviate the data movement bottleneck in modern computing systems. However, current real-world PIM systems have the inherent disadvantage that their hardware is more constrained th…
CPUGPUGraph is a Substrate Across Data Modalities
Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is typically learned in a modality- and task-isolated manner, where graph represe…
Multi-Task Learning