Subgraph Atlas · centered on entity
LLaVA (Visual Instruction Tuning)
technique0 mentions· velocity: stableProjecting CLIP features into an LLM's token space via a simple projector + instruction tuning on GPT-4-generated visual conversations.
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
CLIP (Contrastive Language-Image Pretraining)technique
13 mentions
→ Center atlas here
Kimi K2.5ai model
7 mentions
→ Center atlas here
Qwen 3.6ai model
3 mentions
→ Center atlas here
Visual Instruction Tuningpaper
0 mentions
→ Center atlas here
University of Wisconsincompany
0 mentions
→ Center atlas here
Instruction Tuning (FLAN)technique
0 mentions
→ Center atlas here
Llama 4 Scoutai model
0 mentions
→ Center atlas here