RSS

cloud

Karma: 424

Distil­la­tion Ro­bus­tifies Unlearning

Bruce W. Lee, Addie Foote, alexinf, leni, Jacob G-W, Harish Kamath, Bryce Woodworth, cloud and TurnTrout
Jun 13, 2025, 1:45 PM
220 points
11 comments8 min readLW link
(arxiv.org)

Selec­tive mod­u­lar­ity: a re­search agenda

cloud and Jacob G-W
Mar 24, 2025, 4:12 AM
66 points
2 comments24 min readLW link

[Question] Is weak-to-strong gen­er­al­iza­tion an al­ign­ment tech­nique?

cloudJan 31, 2025, 7:13 AM
22 points
1 comment2 min readLW link

Gra­di­ent Rout­ing: Mask­ing Gra­di­ents to Lo­cal­ize Com­pu­ta­tion in Neu­ral Networks

cloud, Jacob G-W, Evzen, Joseph Miller and TurnTrout
Dec 6, 2024, 10:19 PM
165 points
12 comments11 min readLW link
(arxiv.org)