login sign up

Dust: Pretraining Transformers Without Backpropagation

qlabs.sh · first added by @owenp
saved by
1 person
discussions · 1
Dust: Pretraining Transformers Without Backpropagation 279 pts · 81 comments · Oct 2026 279 pts · 81 comments · Oct 2026
0 people saved or upvoted this
from the discussion · 4
Augmented Lagrangian Predictive Coding: training 1000-layer networks without backpropagation pub.sakana.ai pub.sakana.ai
1 person saved or upvoted this
BOLD: Boolean Logic Deep Learning proceedings.neurips.cc proceedings.neurips.cc
0 people saved or upvoted this
https://www.nature.com/articles/s41467-025-64234-z.pdf nature.com nature.com
0 people saved or upvoted this
https://arxiv.org/pdf/2605.12732 arxiv.org arxiv.org
0 people saved or upvoted this
related HN threads · 1
Backprop Alternative: Augmented Lagrangian Predictive Coding 128 pts · 45 comments · Sep 2026 128 pts · 45 comments · Sep 2026
0 people saved or upvoted this