Models and papers.
Iris-3B
Pixel-space generation & general vision learner
A fully open 3B flow-matching transformer that generates raw RGB pixels directly — no VAE in the loop — and a generative prior that acts as a general vision learner.
Hanqiu Li Cai· Chema Garabito
Oct 2026Open
ENEAS
Embedding-guided Neural Ensemble for Adaptive Segmentation
Name a concept in plain language — ENEAS finds it, segments it, and holds onto that exact instance across an entire image or video.
Javier del Pino· Salvador Rodríguez· Alejandro Garabito· Javier Álvarez· Chema Garabito
May 2026Open
Collaboration
Working on something adjacent?
Datasets, benchmarks, reconstruction pipelines, or a problem where a spatial foundation model would change the unit of work — we would like to hear about it.