FULL STORY
Looped-DiT: Recycled Transformer Blocks Beat Bigger Models
Looped-DiT from SenseTime, Tsinghua and NTU recycles the same transformer blocks across denoising steps instead of stacking deeper networks, letting a small text-to-image model outperform models 6.5x its size.
2026-10-01 ~ 2026-10-04 · 2 episodes · 6 posts
Episode 1 · Looped-DiT: Small Model Beats 6.5x Larger Ones by Reusing Transformer Blocks (2026-10-01, 2 posts)
A new paper, Looped Diffusion Transformer (Looped-DiT), repeatedly reuses a shared Transformer block at each denoising step instead of stacking deeper layers. A 260M-parameter model outperforms one 6.5x larger while using 4.9x less compute.
- Looped DiT: 260M model beats 6.5x larger rival on T2I benchmarks with 4.9x less compute — arankomatsuzaki · 2026-10-01
- Looped-DiT: 260M model beats 6.5x larger rival on text-to-image with 4.9x less inference compute — burny_tech · 2026-10-01
Episode 2 · Looped-DiT: Recycled Transformer Layers Beat Models 6.5x Larger (2026-10-03, 4 posts)
Researchers from SenseTime, Tsinghua and NTU propose Looped-DiT, the first looped Transformer for text-to-image diffusion. With only 260M parameters, reusing shared Transformer blocks within each denoising step beats models 6.5x larger while cutting inference compute by 4.9x.
- Looped-DiT: 260M Looped Model Beats 6.5x Larger Diffusion Models With 4.9x Less Compute — NandoDF · 2026-10-03
- Looped-DiT: 260M looped model beats 6.5x larger ones with 4.9x less inference compute — burny_tech · 2026-10-04
- Looped-DiT: 260M looped model beats 6.5x larger text-to-image rival with 4.9x less compute — Apprehensive_Sky892 · 2026-10-04
- Looped-DiT: the first Looped Transformer for text-to-image generation — liuziwei7 · 2026-10-04