arXiv CSopen access
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
machine learning, deep learning, neural networks
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Record · ID 440351
Retrieved via
Conceptio — every document is proof-bundled with source, license, and retrieval metadata.