Berkeley-NLP

AI & ML interests

We work on a broad range of topics including structured prediction, grounded language, computational linguistics, model robustness, and HCI.

Recent Activity

alsuhr  authored a paper about 2 hours ago

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

alsuhr  authored a paper about 2 hours ago

Abstract Visual Reasoning with Tangram Shapes

alsuhr  authored a paper about 2 hours ago

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

View all activity

Team members 3