The authors examined how an unaligned diffusion transformer learns the feature hierarchy of a frozen visual encoder.
Diffusion models benefit most from teacher features they still lack
A recoverability-based method selects useful teacher layers, weights unresolved tokens and stops alignment when its benefit plateaus.
Chinese Tech
Yongcong Wang · Hingchin Chen · Mingyu Fan · Shuo Jiang · Teer Zhang · Yucong Sun · +3 more
Central South University · The Hong Kong University of Science and Technology · Tsinghua University · The Chinese University of Hong Kong, Shenzhen · SenseTime Research
Research Digest··3 min read
Wang and colleagues study how to choose the teacher layer and duration of representation alignment when training diffusion transformers.
Why this paper
From SenseTime Research and 9 others
In one line
RARE selects the teacher layer with the largest recoverability gap, improving FID and training speed.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓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.
§