Liquid AI Post-Training Lead Details Two Years of SFT/RL/MOPD Shifts
Liquid AI's post-training lead Maxime Labonne explained on a podcast how post-training has evolved dramatically over two years, noting that SFT improves pass@k while RL converges on pass@1.
2026-11-18 ~ 2026-11-18 · 2 related posts
- Liquid AI's Maxime Labonne on post-training: SFT, RL, MOPD and regression — ziv_ravid · 2026-11-18
- Liquid AI post-training head: SFT lifts pass@k, RL sharpens it to pass@1 — ziv_ravid · 2026-11-18