arxivJun 12bullish

Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite

arXiv:2606.11257v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation. Running them entirely on-device benefits privacy, latency, and offline use, but the energy cos

GP1 model #edge-intelligence #energy-efficiency #on-device Read on arxiv →

arxivApr 16bullish

Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving

arXiv:2510.00919v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning-such as solving Olympiad-level physics problems-remains largely unexplored. Inspir

#retrieval-augmented-generation #foundation-models #physics-reasoning Read on arxiv →

arxivApr 4

From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents

arXiv:2604.01733v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems critically depend on retrieval quality, yet no systematic comparison of modern retrieval methods exists for heterogeneous documents containing both text and tabular data. We benchmark ten retrieval strateg

BMHYHY3 models #information-retrieval #benchmark #financial-qa Read on arxiv →