Heemin Kim
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Architecture×1
Frequent co-authors
Research Timeline
2026
MemLLM: End-to-end In-Storage Acceleration of On-device Retrieval-Augmented Generation using Precomputed KV Caches
This paper proposes MemLLM, an in-storage processing architecture that accelerates retrieval-augmented generation on edge devices.
Highlighted terms show continued research focus across papers