GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published 14 days ago • 20
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published 14 days ago • 193
OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments Paper • 2605.18758 • Published Apr 3 • 16