activity
20232026
most citedRegularly Truncated M-estimators for Learning with Noisy Labels

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Pengqi Lu

Scaling Diffusion Transformers (DiTs) to hundreds of layers introduces a structural vulnerability: networks can enter a silent, mean-dominated collapse state that homogenizes token…