Subgraph Atlas · centered on entity
Vision Transformer (ViT)
technique0 mentions· velocity: stableApplying a standard Transformer directly to sequences of image patches, establishing Transformers as the dominant image-recognition backbone.
Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.
0 nodes · 0 edges · loading…
companypersonai_modelproductresearch_labbenchmarkframework
drag to move · scroll to zoom · click a node
Top connections
Googlecompany
356 mentions
→ Center atlas here
Gemini 3 Proai model
19 mentions
→ Center atlas here
Gemini 3 Flashai model
9 mentions
→ Center atlas here
Kimi K2.5ai model
7 mentions
→ Center atlas here
Qwen 3.6ai model
3 mentions
→ Center atlas here
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalepaper
0 mentions
→ Center atlas here
Transformer Self-Attentiontechnique
0 mentions
→ Center atlas here
Flamingo (Cross-Attention VLMs)technique
0 mentions
→ Center atlas here