Article

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

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%.

Part of the event: GroundingPI Releases 4B Physical Intelligence Grounding Foundation Model

This page provides a summary and source link only.