The authors replace fixed layer selection with FuseReg, which trains on normalized means of randomly sampled encoder-layer subsets.
Randomized layer fusion improves image reconstruction and diffusion generation
FuseReg trains decoders and diffusion models on changing subsets of visual encoder layers, reducing their dependence on any fixed fusion.
Top University
Hongyang Du · Yunfei Xie · Junjie Ye · Jiawei Yang · Xiaoyan Cong · Haodong Zhang · +10 more
USC PSI Lab · Brown University · Rice University · University of Aberdeen · University of Notre Dame
Research Digest··2 min read
Du et al.
Why this paper
From USC PSI Lab and 6 others
In one line
FuseReg trains decoders and generators on random layer subsets to bridge the reconstruction-generation gap in representation autoencoders.
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.
§