# GroundAnything: Balancing Parallel Decoding and Precise Visual Grounding with Blockwise Denoising

- Source: arXiv cs.RO
- Published: 2026-10-19T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/k8fcil0ckfi14qom4byq6nzzl
- Original: https://arxiv.org/abs/2609.39600

## Summary

GroundAnything is a 4-billion-parameter visual grounding foundation model that combines parallel decoding with precise object localization through blockwise denoising. Its training integrates pretraining on public datasets, direct conversion from autoregressive to diffusion, supervised fine-tuning, and GRPO-based reinforcement post-training.