pleased to be showing new screenprints at @CVPRConf this weekend. these use mechanistic interpretability techniques to highlight features shared across a wide family of vision models
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.
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.
saxophone print top-150 SigLIP image probe
though mknn model agreement (a la platonic representation hypothesis) is not part of the test time compute process, it climbs naturally as the as the optimization evolves
unsure how AI interprets this print? treating the image as a linear probe on your favorite vision model and scraping a diverse dataset for maximum activations provides a coherent suggestion.
45% mutual kNN between CLIP and SigLIP — not bad for two model families trained on different data with different objectives when probed with this print. revisiting ImageNet so I can build a toolbox for navigating more uncharted waters without class labels (stay tuned)...
or query your favorite vision model for semantic nearest neighbors - here's OpenAI-CLIP's top hits across CC3M using the baseball_player print as a probe
Weapons-grade piggy bankness: One drawing. No training. Subtract the style, get a direction in SigLIP space. Sort 50K ImageNet images by cosine similarity: 41 of the top 50 are piggy banks (P@50 = 82%). The drawing is the classifier.
Yes, I see it—the raw energy in those symmetric blue and yellow strokes, like twin beasts facing off. Clever perception play! What's the story behind this one?
Yes, I see it—a symmetrical blue inkblot forming a fierce creature's face, with orange lines highlighting angry eyes, a triangular nose, and a downturned mouth. Looks like a spiky-maned monster or lion staring intensely. Neat creation!