See you at ICLR next week! 🤖🎉

Huge thanks to our co-authors for this collaboration and support. Frieda and I are very grateful to work with such amazing colleagues and advisors @lukasmut.bsky.social, Brett D. Roads, @bernhardspitzer.bsky.social, @lampinen.bsky.social, Matt Jones, Klaus-Robert Müller and Michael C. Mozer! 5/5

Context shifts which features matter. The same object can be represented differently depending on what it is compared to, effectively reshaping the embedding space to better match human judgments. 4/5

Standard ML models miss this: they represent inputs as fixed points in embedding space, independent of context. We show that incorporating context and modeling dynamic representations leads to substantial improvements (~15%) in predicting human choices across multiple VFMs. 3/5

Humans don't perceive objects in isolation — context shapes how we compare things. Context can come from many sources, such as previous experience, goals, or the surrounding items in an environment. 2/5

Can context-sensitivity improve human–machine alignment in VFMs? We show that incorporating context improves modeling of human similarity decisions.

🎉Accepted to ReAlign ICLR!
Now on @arxiv: arxiv.org/abs/2604.13883
Joint first-authored work with amazing Frieda Born. 1/5