| | --- |
| | 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}, |
| | } |
| | ``` |
