Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 324
Viktor Prilepskii
vprilepskii
AI & ML interests
None yet
Recent Activity
updated a model 6 months ago
vprilepskii/Harbinger-24B-biprojected-norm-preserving-abliterated published a model 6 months ago
vprilepskii/Harbinger-24B-biprojected-norm-preserving-abliteratedOrganizations
None yet
upvoted a paper 18 days ago