Article
Distribution Matching Prevents Mode Collapse in Training Reasoning Models
•
2
Marc Dymetman
MarcDymetman
·
AI & ML interests
None yet
Recent Activity
published an article 23 days ago
Distribution Matching Prevents Mode Collapse in Training Reasoning Models upvoted a paper about 1 month ago
Beyond the Imitation Game: Quantifying and extrapolating the
capabilities of language modelsOrganizations
None yet
published an article 23 days ago