# LG AI Research — [CVPR 2022] Large Vision-Language Model: What’s Next?

- Company: LG AI Research (lgresearch.ai)
- Announced: 2022-06-07
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.lgresearch.ai/blog/view?seq=212
- Record: https://forck.live/items/4949-cvpr-2022-large-vision-language-model-what-s-next
- Subject: EXAONE
- Models affected: L-Verse

LG AI Research presents L-Verse, a large vision-language model that performs both text-to-image and image-to-text generation, using only 0.2% of the training data and 5% of the parameters compared to DALL-E, and will be unveiled at CVPR 2022.

## Evidence

Verbatim from https://www.lgresearch.ai/blog/view?seq=212:

> L-Verse can learn with 0.2% of learning data and 5% of parameters compared to DALL-E.

---

Record: https://forck.live/items/4949-cvpr-2022-large-vision-language-model-what-s-next
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md