Author - Mansur Ismagulov
The Tech AI
Get the key points in seconds - a short summary from The Tech AI.
The Korean group ETRI has presented technologies based on generative AI and visual intelligence. The KOALA model generates images in two seconds, which is five times faster than similar models. Additionally, an interactive model called Korava has been developed for working with images and videos, while Ko-LLaVA can answer questions about media files in Korean.
A Korean research team has introduced a technology that combines generative artificial intelligence with visual intelligence to generate an image in two seconds from a sentence input.
The Electronics and Telecommunications Research Institute (ETRI) has three models: KOALA, which generates images five times faster than existing models through sentence input, and Korava, an interactive visual language model that can upload images or videos and answer questions.
Researchers also added visual intelligence technology to ChatGPT to create Ko-LLaVA, an interactive visual language model that can upload images or videos and answer questions about them in Korean.
Source: nst.re.k
The Tech on Telegram Follow The Tech on Telegram
Keep up with the latest technology and startup news.
Related reading
More from this author
News
zypl.ai begins operations in Japan and focuses on next-generation risk models
Mansur Ismagulov
News
Elon Musk's net worth has exceeded $700 billion for the first time
Mansur Ismagulov
Article Interviews
"Central Asian countries should build a joint ecosystem," — Bekhzod Ismoilov on the development of AI in the region
Mansur Ismagulov
Article Interviews
Bloom's Taxonomy and Engineering Levels: A Practical Growth Model
Mansur Ismagulov
Article Useful
How the IT industry in Azerbaijan developed in 2025: key events
Mansur Ismagulov
News
Tajikistan has become a new member of the regional innovation alliance Central Asian Innovation Hubs.
Mansur Ismagulov