works on
inference optimization 1large language models 1load balancing 1mixture-of-experts 1quantization 1

From the 1 of 11 linked papers with an AI index.

most citedThe Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Learning Evidence Highlighting for Frozen LLMs

Shaoang Li, Yanhang Shi, Yufei Li +10

Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evidence Emphasis framework that…