metadata
license: mit
datasets:
- lmms-lab/GQA
- dmarsili/Omni3D-Bench
- cambridgeltl/vsr_random
- snowclipsed/TallyQA
language:
- en
base_model:
- ShilongLiu/GroundingDINO
pipeline_tag: object-detection
tags:
- object-detection
- computer-vision
Model Card for VALOR-GroundingDINO
This is the verified-tuned GroundingDINO model from the paper: No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers
For further information please refer to the project webpage, paper, and repository.
Citation
If you use VALOR in your research, please consider citing our work:
BibTeX:
@misc{marsili2025labelsproblemtrainingvisual,
title={No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers},
author={Damiano Marsili and Georgia Gkioxari},
year={2025},
eprint={2512.08889},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2512.08889},
}