LLMLingua-2

mentions 3 type Organization feed RSS

// recent coverage 3 mentions

04:00

2026-09-17

arxiv.org

artificial-intelligence

Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs

A training-free routing policy called the Tri-Metric Router achieved 0% out-of-memory failures and 88.5 ± 4.4% oracle alignment on out-of-distribution holdouts for retrieval-augmented generation on co…

04:00

2026-08-25

arxiv.org

natural-language-processing

Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems

A new arXiv study (2608.21384v1) finds that Ukrainian and other Cyrillic-script languages face 68-121% token overhead on modern tokenizers and 220% on the older cl100k, compared to English, across nin…

04:00

2026-08-21

arxiv.org

artificial-intelligence

From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG

A new arXiv preprint (2608.19535v1) proposes telemetry-informed adaptive compression for retrieval-augmented generation (RAG) on edge devices, based on experiments on the NVIDIA Jetson AGX Thor with L…

// co-occurs with top 8 entities

arXiv 3 BrUK 1 Brown 1 cl100k 1 Tri-Metric Router 1 NVIDIA T4 1 BM25 1 vLLM 1

// topics top 6 topics

large language models 3 ai research 3 artificial intelligence 2 ai infrastructure 2 natural language processing 1 mlops 1