Why your LLM bill is exploding — and how semantic caching can cut it by 73%

Semantic caching is a practical pattern for LLM cost control that captures redundancy exact-match caching misses. The key ...
IEEE

Transformer-Based API Call Sequence Modeling for Dynamic Malware Detection

Abstract: Dynamic malware detection is based on analyzing behavioral patterns captured in execution logs. In this study, we propose a hybrid deep learning approach that integrates neural networks for ...
IEEE

Query-by-Example Speech Search using Mamba and Random Offset Mixed Padding

Abstract: State-of-the-art approaches to Query-by-Example speech search are usually based on acoustic word embedding (AWE), representing variable-length speech segments with fixed-dimensional vectors ...