Base Labs(@baselabs):Distillation is a common way to prepare a model for RL where learning occurs from a stronger model, and then improves through trial and error. But how much does that better starting point help after RL? We conduct preliminary research on this question across model sizes and reasoning tasks. 🧵

Base Labs

@baselabs

A research lab by @baseten working to advance and democratize open-source intelligence.

加入 July 2026

14 正在關注 2.8K 粉絲

Base Labs@baselabs

2026.09.23 21:52

Distillation is a common way to prepare a model for RL where learning occurs from a stronger model, and then improves through trial and error. But how much does that better starting point help after RL? We conduct preliminary research on this question across model sizes and reasoning tasks. 🧵