Vision Transformer (ViT)

Vision feature extraction model used to extract patch-level features from images in Multimodal-CoT.

Neighborhood — ranked by edge-count

framework

Multimodal-CoT
implements
A two-stage framework that separates rationale generation and answer inference by incorporating vision and language modalities.

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) Modelsconcept0.912
Primary vision model architecture used in both vision-vision and cross-modal alignment experiments
Decision Transformermethod0.718
A model that frames RL as sequence modeling, SOTA from random trajectories.
visual supervisionconcept0.698
Supervisory signals for visual outputs; functional tokens do not require it.
visual reasoningconcept0.695
Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.
Mind's eye visualizationmethod0.692
Technique of building a fluid, three-dimensional vision by closing one's eyes, relying on words and feeling to avoid arbitrary graphical over-specification.
GPT (Generative Pre-trained Transformer)concept0.685
A family of large language models trained on next-token prediction, central example of simulators.
TEM-Transformer (TEM-t)framework0.680
The transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.
Void Transformationconcept0.679
A transformation that cleans out undifferentiated areas, creating a homogeneous zone bounded by differentiated structure, preserving distinctness.