knowledge distillation

3 statements across 3 episodes · 2 bullish · 0 bearish · 3 people on the record · first statement Dec 24, 2024 by Loubna Ben Allal · across every show →

Everything said about knowledge distillation, oldest first

Dec 24, 2024 positive
Insight
Ben Allal: Distilling from large models avoids small-model self-training collapse
“I think if you do that approach, it's normal to observe this kind of behavior because the quality is going to be worse because the model is already small, and then if you train it just on these generations, you shouldn't expect it to become better. But what we…”
Loubna Ben Allal Dec 24, 2024 ▶ 4:56 Best of 2024: Synthetic Data / Smol Models, Loubna Ben Allal, HuggingFace [LS Live! @ NeurIPS 2024]
Mar 23, 2025 positive
Insight
Agarwal: Distilling a Large Model Outperforms Direct Training on the Same Data
“This is something that people have found again and again, that basically you can train a model on some data, or you can train a bigger model on that data and distill that model to another model, and that distill model is better.”
Rishabh Agarwal Mar 23, 2025 ▶ 5:54 The Magic of LLM Distillation — Rishabh Agarwal, Google DeepMind
Feb 12, 2026
Assertion Partly supported
Jeff Dean: Distillation originated to compress 50-model ensembles into serviceable form
“Distillation was originally motivated because we were seeing that we had a very large image data set at the time, you know, three hundred million images that we could train on with, you know, I forget, like 20,000 categories or something, so much bigger than I…”
Jeff Dean Feb 12, 2026 ▶ 3:52 The AI Frontier: from Gemini 3 Deep Think distilling to Flash — Jeff Dean
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.