---
license: apache-2.0
language:
- en
---

**VLE** (**V**isual-**L**anguage **E**ncoder) is an image-text multimodal understanding model built on the pre-trained text and image encoders. 
It can be used for multimodal discriminative tasks such as visual question answering and image-text retrieval. 
Especially on the visual commonsense reasoning (VCR) task, which requires high-level language understanding and reasoning skills, VLE achieves significant improvements.

For more details see [https://github.com/iflytek/VLE](https://github.com/iflytek/VLE).

Online VLE demo on Visual Question Answering: [https://huggingface.co/spaces/hfl/VQA_VLE_LLM](https://huggingface.co/spaces/hfl/VQA_VLE_LLM)