metadata
license: apache-2.0
base_model: Qwen/Qwen3-VL-2B-Instruct
tags:
- vision
- multimodal
- safety
- guard-model
- icml-2026
pipeline_tag: image-text-to-text
OmniVL-Guard-2B
A safety guard model for vision-language content moderation, accepted at ICML 2026. Fine-tuned from Qwen/Qwen3-VL-2B-Instruct.
Usage
from transformers import Qwen3_VLForConditionalGeneration, AutoProcessor
model = Qwen3_VLForConditionalGeneration.from_pretrained("SJJ0854/OmniVL-Guard-2B")
processor = AutoProcessor.from_pretrained("SJJ0854/OmniVL-Guard-2B")
Training Data
Refined-SFT and RL datasets available at SJJ0854/FSFR.
Citation
@inproceedings{omnivlguard2026,
title={OmniVL-Guard: A Safety Guard for Vision-Language Models},
booktitle={International Conference on Machine Learning (ICML)},
year={2026}
}