# GroundingPI releases 4B grounding foundation model, averaging 73.68% across 34 benchmarks

- Source: arXiv cs.RO
- Published: 2026-10-19T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/eht028jv1ppda1khw7k0ue9uc
- Original: https://arxiv.org/abs/2609.39601

## Summary

GroundingPI is a 4B-parameter grounding foundation model that outputs points and boxes as quantized coordinates in a shared vocabulary; its training combines multimodal and spatial pretraining, supervised fine-tuning, and GRPO reinforcement learning. It averages 73.68% across 34 grounding benchmarks and 44 baselines, above GPT-6 Astra's 71.54%.