Dnotitia Unveils STAR-KV, Achieving UP to 20x KV Cache Compression, Selected as an ICML 2026 Spotlight Paper

Dnotitia introduced STAR-KV, an advanced KV cache compression technology that can achieve up to 20x compression, significantly accelerating long-context AI attention computations and generation throughput. This innovation was selected as a Spotlight paper at ICML 2026, underscoring its importance in AI research.