If I describe a walk through something with known spatial structure—the Louvre, NYC, the human body—are there maps in the model that represent location or adjacency the way there for in-context maps? (e.g., https://arxiv.org/abs/2501.00070)
If you are inspired by this idea, you can reach out to the authors for collaboration or cite it:
@misc{holtzman-do-outofcontext-representation-2025,
author = {Holtzman, Ari},
title = {Do Out-of-Context Representation Maps Exist?},
year = {2025},
url = {https://hypogenic.ai/ideahub/idea/xfmuQ4zdCKPsyhiejSml}
}Please sign in to comment on this idea.
No comments yet. Be the first to share your thoughts!