Snapshot from Jul 19, 2026 at 14:14 UTC. For live data and tracking: View Live
Tech tech breakthrough

Dnotitia Unveils STAR-KV AI Breakthrough

Analysis based on 6 articles · First reported Jul 01, 2026 · Last updated Jul 02, 2026

Sentiment
70
Attention
4
Articles
6
Market Impact
General
Live prominence charts, article sentiment distribution, and event development timeline available on the Ergen Dashboard

The release of STAR-KV by Dnotitia, a technology that significantly compresses KV cache and speeds up AI inference, is expected to positively impact the AI infrastructure market. This innovation could lead to lower costs and faster processing for large language models, benefiting companies involved in AI development and deployment. The recognition by International Conference on Machine Learning further validates the technology's potential.

Artificial intelligence Semiconductor industry Software

Dnotitia, in collaboration with UC San Diego's VVIP Lab, has unveiled STAR-KV, a new technology for KV cache compression in long-context AI. This innovation can compress the KV cache by up to 20x and improve attention computation speed by up to 6.9x, as well as overall generation throughput by up to 3.1x. The STAR-KV paper was selected as a Spotlight paper at ICML 2026, one of the world's leading machine learning conferences. This development addresses a key bottleneck in AI infrastructure, reducing GPU memory usage and inference costs for large language models. Dnotitia plans to further advance STAR-KV for real-world AI service environments and explore its application to open-source LLM inference frameworks.

90 Dnotitia released paper and source code
75 Dnotitia developed technology
oth
Dnotitia developed and released STAR-KV, a significant AI technology for KV cache compression, enhancing its reputation and potential market position in AI infrastructure.
Importance 100.0 Sentiment 75.0
oth
ICML 2026 selected the STAR-KV paper as a Spotlight paper, validating the significance and quality of the research and providing a platform for its announcement.
Importance 70.0 Sentiment 50.0
per
Myung-Keun Chung, as CEO of Dnotitia, provided commentary on the significance of STAR-KV, highlighting Dnotitia's commitment to advancing AI inference.
Importance 40.0 Sentiment 60.0
stock
Alphabet Inc.'s TurboQuant is mentioned as a competing or related technology in KV cache compression, indicating Alphabet Inc.'s presence in this evolving AI field.
Importance 30.0 Sentiment 20.0
loc
South Korea — Seoul is the location where ICML 2026 will be held, providing the venue for the presentation of the STAR-KV paper.
Importance 10.0 Sentiment 0.0
cnt
South Korea is the country where Dnotitia is based and where ICML 2026 will be held.
Importance 10.0 Sentiment 0.0
ERGEN INTELLIGENCE
Track this event live

Set up alerts, explore entity relationships, search across thousands of events, and build custom intelligence feeds.

Open Dashboard

About Ergen

Ergen is a news intelligence platform that converts raw news articles into structured data. It tracks events, entities, and the relationships between them, with sentiment and attention metrics derived from thousands of articles. Pages on this site are daily static snapshots from the platform's live database. For real-time tracking, search, and alerts, the full dashboard is at app.ergen.ai.