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...
2025 Modern Governance Forum at Tsinghua Highlights China's Planning System and Global Governance Risks in an Era of Transformation
BEIJING, Nov. 20, 2025 /PRNewswire/ -- Tsinghua University hosted the 2025 Modern Governance Forum on November 16, convening scholars, policymakers, and practitioners for in-depth discussions on "Global and Public Governance in an Era of...