Vision Transformer (ViT) Models

Primary vision model architecture used in both vision-vision and cross-modal alignment experiments

Neighborhood — ranked by edge-count

paper

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Vision Transformer (ViT)method0.912
Vision feature extraction model used to extract patch-level features from images in Multimodal-CoT.
self-model (transformer)concept0.739
The transformer's model of itself as a predictive text engine, developed through in-context learning.
Among 78 vision models on Places-365, models that solve more VTAB tasks tend to be more aligned with each other, with high-performance models forming a tightly clustered setfinding0.728
Empirical result showing alignment increases with model competence
Video World Modelconcept0.717
Secondary substrate demonstrating cross-modal applicability of manifold steering.
Among 78 vision models, those solving more VTAB tasks (higher transfer performance) show higher mutual nearest-neighbor alignment with each otherfinding0.710
Key empirical finding establishing that representational alignment correlates with model competence
Decision Transformermethod0.708
A model that frames RL as sequence modeling, SOTA from random trajectories.
TEM-Transformer (TEM-t)framework0.698
The transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.
Perceptual Field Modelframework0.695
Model introduced in Figure 2 explaining how collective intelligence expands the spatiotemporal perceptual field of a group beyond any individual member's capacity.