GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public datasets and dedicated data engines. Again...
| Authors | Qize Yu, Lianrui Fan, Boyu Chen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 30 September 2026 |
| Last updated at source | 30 September 2026 |
Connected in the knowledge graph
- GroundingPI/GroundingPIModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.