arXiv cs.CV: handwriting/OCR
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
접지하기PI: 시각 원시 요소를 활용한 물리 지능을 위한 접지 기반 모델
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.