Compressed (caveman) reasoning traces train models to reason in ~2-3x fewer tokens at equal or better accuracy. For full ablation: sibling collection.
👋 Open to Work
Marco De Santis
marcodsn
AI & ML interests
LMs, datasets, cats?
Recent Activity
liked a Space 11 days ago
AxiomicLabs/Open_SLM_Leaderboard updated a model about 2 months ago
nullsilver/alpha-sys-1-3B updated a model about 2 months ago
nullsilver/alpha-sys-1-450MOrganizations
Compressed (caveman) reasoning traces train models to reason in ~2-3x fewer tokens at equal or better accuracy. For full ablation: sibling collection.
All ablation arms + dataset variants behind the caveman reasoning-compression study. For headline artifacts: see the main collection.
Synthetic Online Conversations
Synthetic Persona Bank
My submissions for the Agents-MCP-Hackathon