Memory Grafting improves language-model benchmarks by grafting offline hidden-state memory from a larger model into a recipient model using n-gram lookups and lightweight adapters, outperforming MoE and vanilla Engram baselines at 0.92B and 2.8B scales.
Chameleon: a heterogeneous and disaggregated accelerator system for retrieval-augmented language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
A comprehensive review of scaling paths for superconducting quantum computers, with resource and sensitivity analyses for utility-scale applications under realistic error distributions.
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.
citing papers explorer
-
Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
Memory Grafting improves language-model benchmarks by grafting offline hidden-state memory from a larger model into a recipient model using n-gram lookups and lightweight adapters, outperforming MoE and vanilla Engram baselines at 0.92B and 2.8B scales.
-
How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits
A comprehensive review of scaling paths for superconducting quantum computers, with resource and sensitivity analyses for utility-scale applications under realistic error distributions.
-
A Survey on Retrieval-Augmented Text Generation for Large Language Models
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.