The authors reinterpret Diffusion-DPO, a method that learns from pairs of preferred and dispreferred images, through the manifold hypothesis.
Geometry-aware alignment keeps diffusion models near natural image structure
APO uses a reference model’s local geometry to constrain risky diffusion updates while permitting safer semantic changes.
Chinese Tech
Lei Wang · Zhen Wang · Yuexiang Xie · Yaliang Li
Sun Yat-Sen University · Alibaba Group
Research Digest··3 min read
Wang et al.
Why this paper
From Alibaba Group and Sun Yat-Sen University
In one line
Anisotropic geometry-aware optimization prevents off-manifold drift in diffusion model preference alignment.
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
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§