---
language: 
  - en
tags:
- vision-language
- clip
- vilt
datasets:
- lil-lab/kilogram-data

---

KiloGram dataset and code repo: https://github.com/lil-lab/kilogram

Preprocessed training and evaluation data: https://huggingface.co/datasets/lil-lab/kilogram-data

# Citation

```bibtex
@misc{ji2022abstractvisualreasoningtangram,
      title={Abstract Visual Reasoning with Tangram Shapes}, 
      author={Anya Ji and Noriyuki Kojima and Noah Rush and Alane Suhr and Wai Keen Vong and Robert D. Hawkins and Yoav Artzi},
      year={2022},
      eprint={2211.16492},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2211.16492}, 
}
```