GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published 14 days ago • 251
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding Paper • 2603.22458 • Published Mar 23 • 99
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published 14 days ago • 74