CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences Paper • 2503.12491 • Published Mar 16, 2025
GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions Paper • 2504.10146 • Published Apr 14, 2025
Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling Paper • 2504.09261 • Published Apr 12, 2025 • 1
