---
base_model:
- OpenGVLab/InternVL3_5-1B-Instruct
language:
- en
license: mit
metrics:
- accuracy
tags:
- visual-reasoning
- fine-grained-vqa
- fine-grained-recognition
pipeline_tag: image-text-to-text
library_name: transformers
---

# Model Card for TWIN-InternVL3_5-1B

This repository contains the InternVL3.5-1B model post-trained on the TWIN dataset, as introduced in the paper [Same or Not? Enhancing Visual Perception in Vision-Language Models](https://arxiv.org/abs/2512.23592).

TWIN is a large-scale dataset of 561,000 image-pair queries designed to enhance the perceptual abilities of Vision-Language Models (VLMs). It tasks models to determine whether two visually similar images depict the same object, encouraging attention to nuanced visual cues. Fine-tuning on TWIN yields significant gains in fine-grained recognition across various domains like art, animals, plants, and landmarks.

## Resources

- **Project Page:** [https://glab-caltech.github.io/twin/](https://glab-caltech.github.io/twin/)
- **Paper:** [Same or Not? Enhancing Visual Perception in Vision-Language Models](https://arxiv.org/abs/2512.23592)
- **Code Repository:** [https://github.com/damianomarsili/TWIN](https://github.com/damianomarsili/TWIN)
- **Dataset:** [glab-caltech/TWIN](https://huggingface.co/datasets/glab-caltech/TWIN)
- **Benchmark Suite:** [glab-caltech/FGVQA](https://huggingface.co/datasets/glab-caltech/FGVQA)

## Citation

If you use TWIN in your research, please consider citing the work:

```bibtex
@misc{marsili2025notenhancingvisualperception,
      title={Same or Not? Enhancing Visual Perception in Vision-Language Models}, 
      author={Damiano Marsili and Aditya Mehta and Ryan Y. Lin and Georgia Gkioxari},
      year={2025},
      eprint={2512.23592},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.23592}, 
}
```