← Back to KHAO

Apple ·

Locking Pretrained Weights via Deep Low-Rank Residual Distillation

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

★ Tier-1 Source

Bottom banner.

Locking Pretrained Weights via Deep Low-Rank Residual Distillation.

Key facts

Summary

Authors Keitaro Sakamoto†**, Pierre Ablin, Federico Danieli, Marco Cuturi. The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardware and software platforms. In some cases, however, concerns on modifying these weights towards unauthorized uses may outweigh the pros of giving users such a freedom. The team propose 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 (DLR-Net) of comparable parameter count, forcing activation memory that grows linearly with depth during backpropagation.

Read full article at Apple Machine Learning →

#Apple