arxiv:2505.02222
Michael Pust
essentialpust
AI & ML interests
None yet
Recent Activity
authored
a paper
28 days ago
Practical Efficiency of Muon for Pretraining
authored
a paper
about 2 months ago
Rethinking Reflection in Pre-Training
upvoted
an
article
4 months ago
Optimizing Pretraining Data Mixes with LLM-Estimated Utility
Organizations
None yet
