The authors introduce FiST, a Transformer architecture that implements a few-step latent rollout for image generation. They use a distill-then-refine procedure: first, the model is initialized by distilling a pretrained teacher via regression on selected latent states, then refined end-to-end against real data using adversarial and classification objectives. On class-conditional ImageNet 256x256, FiST achieves FID 1.11 with three generation stages and FID 1.15 with two, outperforming some other few-step methods and approaching many-step models. All training occurs in latent space without image decoding, and the approach does not directly minimize Fréchet distance. The results demonstrate that end-to-end optimization of the complete rollout can produce high-quality few-step generation, with ablations showing benefits from longer distillation, REPA-based discriminator features, and cross-stage hidden communication.
Three-stage latent generator reaches 1.11 FID on ImageNet
FiST combines teacher distillation with end-to-end adversarial refinement to generate class-conditional 256-pixel images in two or three stages.
Chinese Tech
Xiaoran Xu · Yujing Wang
ByteDance
Research Digest··3 min read
In one line
A distill-then-refine latent rollout approach with a staged Transformer achieves FID 1.11 on ImageNet 256x256 without Fréchet losses.
Before you read this
Three ideas this paper builds onadversarial trainingTraining a model on adversarially perturbed inputs to make it robust to attacks, often trading some clean accuracy for resilience.9 papers →looped transformerA transformer architecture whose weights are reused across repeated passes, trading loop count for depth, compute, or accuracy.27 papers →latent communicationLatent communication transfers information between models via internal states like KV caches instead of explicit text.16 papers →
Read it as
Xu and Wang train a few-step image generator by first imitating a pretrained teacher, then optimizing the entire sequence of latent transitions against real ImageNet data.
The authors introduce Flow-in-Stage Transformer, or FiST, which repeatedly applies a shared Transformer to move a noisy latent representation toward a generated image latent.
How it works
stage by stageThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.