Yunghee Lee
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1
Frequent co-authors
Research Timeline
2026
Rethinking FID Through the Geometry of the Reference Dataset
The paper argues that the standard FID metric is unreliable because its performance depends significantly on the geometric structure and density of the reference dataset, not just the sample quality.
Highlighted terms show continued research focus across papers