arXivZixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore, William T. Freeman, Congyue Deng, Marin SoljačićMon, May 25, 2026, 10:01 AM PDT

score 16.5

Single AI model generates and upscales images at any resolution

Original: Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution

Writing ELI5 summary…