This paper fixes a hidden flaw in a popular image tokenizer (FSQ) with a simple one-line change to its activation function.
Flow Matching is like teaching arrows to push points from a simple cloud (source) to real pictures (target); most people start from a Gaussian cloud because it points equally in all directions.
The paper shows that many AI image generators are trained to prefer one popular idea of beauty, even when a user clearly asks for something messy, dark, blurry, or emotionally heavy.
This paper fixes two big problems in image-making AI that builds pictures step by step: it often practices with perfect answers (teacher forcing) but must perform using its own imperfect guesses later, and the earliest coarse steps are much harder than the later fine steps.
EditThinker is a helper brain for any image editor that thinks, checks, and rewrites the instruction in multiple rounds until the picture looks right.