trends.barnas.net

method · first seen 13 Oct 2026

reinforcement learning from distilled supervision

Also: D2RL

Training a model with reinforcement learning after distillation to address poor generalization of supervised fine-tuning and sparse rewards.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

GUI visual grounding