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
PapersCodeDiscussion
Earliest sources
- GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement LearningPapers · 13 Oct 2026 · Qingsong Xie, Jiahao Tian, Jiacheng Tang, Zhifeng Li, Madalina Ciobanu, Navan Pr…
Latest sources
- GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement LearningPapers · 13 Oct 2026 · Qingsong Xie, Jiahao Tian, Jiacheng Tang, Zhifeng Li, Madalina Ciobanu, Navan Pr…