Just a fun hack I did while bored over the weekend. My wife was busy shopping, it got me thinking that can VLMs solve the indoor location problem in a mall? Can I just show a VLM a map and an image and have it doa good enough job locating me? I hacked this P.O.C and it seems to work.
Comments URL: https://news.ycombinator.com/item?id=44476339
Points: 35
# Comments: 0
https://arjo129.github.io/blog/5-7-2025-From-Photos-To-Positions-Prototyping.html
Connectez-vous pour ajouter un commentaire
Autres messages de ce groupe
Hi everyone — I’m Clark, creator of Keeps, a way to send physical postcards that play your voice with a quick QR code scan.
WHAT IT IS Upload a photo (or pick from Unsplash), write a message, op
![GLM-4.5: Agentic, Reasoning, and Coding (Arc) Foundation Models [pdf]](data:image/png;base64,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 "GLM-4.5: Agentic, Reasoning, and Coding (Arc) Foundation Models [pdf]")
Article URL: https://www.arxiv.org/pdf/2508.06471
Comments URL: https://news.ycomb
Article URL: https://typo.social/@Hilary/114845913381245488
