Loop-μP: Residual Scaling and Hyperparameter Transfer in Looped Transformers Paper • 2606.18524 • Published 18 days ago • 1
AI Release Week Thread (26 Oct 2026) Collection AI Release Week Thread (26 Oct 2026) • 21 items • Updated 3 days ago
AI Release Week Thread (26 Oct 2026) Collection AI Release Week Thread (26 Oct 2026) • 21 items • Updated 3 days ago