Dnotitia Unveils STAR-KV, Achieving UP to 20x KV Cache Compression, Selected as an ICML 2026 Spotlight Paper
Introduces a low-rank-based approach to KV cache compression, one of the key bottlenecks in long-context AI Speeds up attention computation by up to 6.9x and overall generation throughput by up to 3.1x, moving beyond memory savings to faster...
Vmake Integrates ICML-Accepted BridgeRemoval Algorithm for Advanced AI Video Object Removal
PALO ALTO, Calif., May 21, 2026 /PRNewswire/ -- Vmake has officially integrated BridgeRemoval, a next-generation AI algorithm developed to improve the quality and speed of video object removal. The research paper behind this algorithm has been...