StockDuty ← Dashboard Oct 15, 2026 03:48 AM ET
SignalTech/AI

GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning

GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning

What happened: Researchers introduced GroundGUI, built on the ScreenRef GUI grounding dataset and a Distillation-to-Reinforcement Learning (D2RL) method, training GroundGUI-8B from Qwen3-VL-8B-Instruct via sequential SFT and D2RL. Key numbers: ScreenRef contains 586K screenshots and over 633K referring expression instances. Why it matters: The authors report state-of-the-art results among 8B-scale agents, with performance comparable or superior to models trained on closed-source data.
Researchers introduced GroundGUI, built on the ScreenRef GUI grounding dataset and a Distillation-to-Reinforcement Learning (D2RL) method, training GroundGUI-8B from Qwen3-VL-8B-Instruct via sequential SFT and D2RL.
The authors report state-of-the-art results among 8B-scale agents, with performance comparable or superior to models trained on closed-source data.
Sources