[R] Measuring Vision-Language STEM Skills of Neural Models

We introduce a new challenge to test the STEM skills of neural models, which has been accepted by ICLR 2024.

Authors: Jianhao Shen, Ye Yuan, Srbuhi Mirzoyan, Ming Zhang, Chenguang Wang

* **Paper:** [https://arxiv.org/abs/2402.17205](https://arxiv.org/abs/2402.17205)
* **Leaderboard:** [https://huggingface.co/spaces/stemdataset/stem-leaderboard](https://huggingface.co/spaces/stemdataset/stem-leaderboard)
* **Dataset:** [https://huggingface.co/datasets/stemdataset/STEM](https://huggingface.co/datasets/stemdataset/STEM)
* **Code:** [https://github.com/stemdataset/STEM](https://github.com/stemdataset/STEM)

**Abstract:** The problems in the real world often require solutions, combining knowledge from STEM (science, technology, engineering, and math). Unlike existing datasets, our dataset requires the understanding of multimodal vision-language information of STEM. Our dataset features one …

abstract authors challenge engineering iclr iclr 2024 knowledge language machinelearning math measuring science skills solutions stem technology test vision vision-language world