Shucheng Li
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1
Frequent co-authors
Research Timeline
2026
Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
This paper investigates the phenomenon of 'copying' in Distribution Matching Distillation (DMD), finding that high-dimensional distillation causes student models to spontaneously reproduce the teacher's original noise-data pairings due to geometric constraints.
Highlighted terms show continued research focus across papers