A single model unifies retrieval and context compression for on-device RAG via shared representations, matching traditional RAG performance at 1/10 context size with no extra storage.
Mobilerag: A fast, memory-efficient, and energy-efficient method for on-device RAG
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PuppyChatter is a new framework that combines SDK-like usability with model-abstraction vendor neutrality for LLM application development.
citing papers explorer
-
A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation
A single model unifies retrieval and context compression for on-device RAG via shared representations, matching traditional RAG performance at 1/10 context size with no extra storage.
-
Accelerating AI-Powered Research: The PuppyChatter Framework for Usable and Flexible Tooling
PuppyChatter is a new framework that combines SDK-like usability with model-abstraction vendor neutrality for LLM application development.