Urgent.News

What's breaking now, across thousands of outlets.

AI

'AI artists' perform improvised jazz at Jarasum Jazz Festival

Artificial intelligence (AI) models developed by a research team led by Korea Advanced Institute of Science and Technology (KAIST) professor Nam Ju-han made their debut at one of Korea’s leading jazz festivals, performing improvised jazz alongside human artists. According to the university Friday, the team showcased human-AI music collaboration technology that analyzes the flow of human…

'AI artists' perform improvised jazz at Jarasum Jazz Festival

The Korea Advanced Institute of Science and Technology (KAIST) showcased a groundbreaking collaboration between artificial intelligence (AI) and human jazz musicians at the 23rd Jarasum Jazz Festival in Gapyeong County, Gyeonggi Province, from October 9 to 11. A research team led by KAIST professor Nam Ju-han presented AI models that were able to analyze the real-time flow of human performances and generate improvised accompaniment or take over performances entirely.

During the festival, 12 human jazz artists participated in 26 pieces across 12 performances, collaborating with the AI in a manner distinct from existing music AI services. The AI technology, unique in its ability to work alongside jazz musicians, enabled collaboration with human musicians, a genre known for its improvisational nature.

Jazz performances often involve adjustments in tempo or the creation of new melodies based on the musicians' feelings in the moment. As each piece can be performed differently, musicians must listen to one another and adjust their playing accordingly.

Written by urgent.news from The Korea Times's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at koreatimes.co.kr →

More in AI

Microsoft unveils MAI-Base-2, a MoE model with 2.8T total and 80B active parameters, claiming 4x-12x more pretraining FLOPs-efficiency than DeepSeek-V4-Pro-Base (Microsoft AI)

In June, we announced MAI-Thinking-1, a general-purpose foundation model post-trained on top of MAI-Base-1 with strong reasoning performance.

  • MAI-Base-2 model unveiled with 2.8T total and 80B active parameters
  • 4-12 times more efficient in pre-training FLOPs than DeepSeek-V4-Pro-Base
  • Model trained on MAI-Base-1, outperforms open-weight models in tests

More from Friday 16 October →