Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

NeurIPSSpotlight2025

Authors
Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collapse when asked to magnify far beyond that regime…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

alignment

← All NeurIPS 2025 Spotlight papers · Browse the whole archive