Each print's unique backlighting element is provided by a TIPS model. This shows spatial patch level activations highlighting visually where that model attends to when activating its analogous feature.
Behind the scenes I have a basket of metrics to evaluate how the prints are interpreted. For example, in the spirit of Platonic Representation Hypothesis I evaluate mutual knn - using the print itself to gauge concept coherence across models.
If you are at CVPR drop by - six pieces are on display today and tomorrow just behind the Google booth in the #CVPR2026 art show. I'll be there for daily artist talks on the official schedule or DM if you'd like to meet up and chat.
Each print's unique backlighting element is provided by a TIPS model. This shows spatial patch level activations highlighting visually where that model attends to when activating its analogous feature.
Each print's unique backlighting element is provided by a TIPS model. This shows spatial patch level activations highlighting visually where that model attends to when activating its analogous feature.
Behind the scenes I have a basket of metrics to evaluate how the prints are interpreted. For example, in the spirit of Platonic Representation Hypothesis I evaluate mutual knn - using the print itself to gauge concept coherence across models.