Author

Federico Danieli

h-index 4 View on Semantic Scholar

We have 1 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning May 2026

Locking Pretrained Weights via Deep Low-Rank Residual Distillation

This work proposes DLR-Lock, a method where the purveyor of the model purposely replaces each pretrained MLP in their model with a deep low-rank residual network of comparable parameter count, forcing activation memory that grows linearly with depth during backpropagation, and exploits the inference-training asymmetry...

Keitaro Sakamoto, Pierre Ablin, Federico Danieli et al. · arXiv.org · 0 citations