The authors start from a standard Diffusion Transformer (DiT) and replace its block with a shared core that is applied repeatedly.
Loop-specific targets let diffusion transformer improve with extra inference loops
On ImageNet 256x256, a model with 60% fewer parameters outperforms a dense baseline by 3.34 FID.
Top University
Mohammad Mahdi Derakhshani · Pedro M. P. Curvo · Gertjan J. Burghouts · Jan-Willem van de Meent · Cees G. M. Snoek
University of Amsterdam · TNO
Research Digest··3 min read
Derakhshani et al.
Why this paper
From University of Amsterdam and TNO
In one line
LiFT improves ImageNet generation by repeatedly applying a shared DiT core with depth-specific trajectory targets, cutting parameters and compute versus a dense DiT baseline.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (4 noted)
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§