Barbarians at the Gate: How AI is Upending Systems Research Paper • 2510.06189 • Published Oct 7, 2025 • 9
Approximate Caching for Efficiently Serving Diffusion Models Paper • 2312.04429 • Published Dec 7, 2023 • 2
Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation Paper • 2502.15734 • Published Feb 5, 2025 • 4
RCStat: A Statistical Framework for using Relative Contextualization in Transformers Paper • 2506.19549 • Published Jun 24, 2025 • 3