2 papers
cs.AI2026
SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance
Rya Sanovar, Srikant Bharadwaj, Hritvik Taneja +1
Retrieval-Augmented Generation (RAG) injects LLM queries with relevant documents to improve response quality. This injection increases prompt length and slows time to first token (…
cs.AR2023
The Mirage of Breaking MIRAGE: Refuting the HPCA-2023 Paper "Are Randomized Caches Truly Random?"
Gururaj Saileshwar, Moinuddin Qureshi
The HPCA-2023 paper "Are Randomized Caches Truly Random?" makes the claim that "MIRAGE is broken" while relying on two faulty assumptions: (1) starting from a severely compromised…