t-SNE

Findings

• IC-069EVA-CLIP's dense patch features are semantically contaminated by surrounding context, degrading their spatial quality [eval]
• IC-070Region-language alignment fine-tuning degrades EVA-CLIP's spatial awareness as measured by unsupervised segmentation [eval]
• IC-1171Pre-trained ViT, MAE, and ResNet50 (supervised and MoCo v2) place visually similar but semantically distinct ImageNet classes (mop, broom, puck, crutch) in close proximity in their feature space [primary]
• IC-279GP-LVM produces less structured latent representations and lower generative-classification accuracy than QEP-LVM on oil flow and MNIST [eval]
• IC-565Phi-3's residual stream encodes format instructions as linear directions, evidenced by cosine similarity and vocabulary-space projections [supporting]