GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published Sep 30 • 58
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published Sep 30 • 151
xmj2002/hubert-base-ch-speech-emotion-recognition Audio Classification • Updated May 16, 2023 • 584 • 62