A train-free phrase memory system for LLMs uses SSD-backed hierarchical storage and early-exit predictive prefetching to improve downstream accuracy without backbone training.
Gonzalez, Hao Zhang, and Ion Stoica
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
A train-free phrase memory system for LLMs uses SSD-backed hierarchical storage and early-exit predictive prefetching to improve downstream accuracy without backbone training.