Dnotitia Unveils STAR-KV, Achieving UP to 20x KV Cache Compression, Selected as an ICML 2026 Spotlight Paper
PR Newswire
SEOUL, South Korea, July 1, 2026
Introduces a low-rank-based approach to KV cache compression, one of the key bottlenecks in long-context AISpeeds up attention computation by up to 6.9x and overall generation throughput by up to 3.1x, moving beyond memory savings to faster inferenceSelected as a Spotlight paper at ICML 2026, representing about 2.2% of reviewed submissions and about 8.4% of accepted papersFollowing the attention around Google's TurboQuant at ICLR 2026, STAR-KV presents another approach to advancing KV cache compressionPaper available on arXiv; source code released on GitHubSEOUL, South Korea, July 1, 2026 /PRNewswire/ -- Dnotitia Inc. (Dnotitia), a company specializing in long-term memory AI and semiconductor-based AI infrastructure technologies, has released the paper and source code for "STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control." The technology was developed through a joint research effort involving UC San Diego's VVIP Lab and Dnotitia researchers, and the paper was selected as a Spotlight paper at ICML 2026 (International Conference on Machine Learning 2026), one of the world's leading conferences in machine learning.
