EPISODE · Apr 26, 2026 · 11 MIN
SSD: Self-Distillation for Code Generation Without a Teacher
from Mastering Language Models: From Architecture to Optimization
A post-training efficiency episode on simple self-distillation: using a model’s own sampled code outputs as supervised fine-tuning data without a verifier, teacher, or reinforcement learning.
NOW PLAYING
SSD: Self-Distillation for Code Generation Without a Teacher
No transcript for this episode yet
Similar Episodes
Mar 26, 2026 ·1m
Mar 19, 2026 ·34m
Feb 18, 2026 ·11m
Feb 11, 2026 ·45m