---
datasets:
- lmms-lab/RefCOCOg
language:
- en
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
pipeline_tag: zero-shot-object-detection
---
An REC ehanched Qwen 2.5VL 3B with VLM-R1 reinforcement learning. 

cite: arxiv.org/abs/2504.07615