SF-Foundation PRO

SF-Foundation

·

AI & ML interests

None yet

Recent Activity

published a model 6 days ago

SF-Foundation/Gemma4-26B-sft-FP8-dynamic

upvoted a paper 6 days ago

Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL

upvoted a paper 6 days ago

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

View all activity

Organizations

SF-Foundation 's Spaces 1

Trackio