works on
cross-modal attention 1image understanding 1masked diffusion models 1multimodal generation 1self-correcting sampling 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes

Minh-Quan Le, Armand Comas, Alexandros Lattas +7

The paper proposes a self‑correcting framework called SC‑CMJP that couples image understanding and generation via cross‑modal attention in masked diffusion models, and introduces a…