conftrace_

delayed generalization

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

grokking (1) input-output mapping (1) neural network (1) embedding transfer (1) linear region (1) phase transition (1) knowledge distillation (1) robustness (1)

Papers

Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model ICLR 2025 Deep Networks Always Grok and Here is Why ICML 2024