---
title: "Zhao Song — papers of 2023 — 2 papers, the most cited first"
description: "Zhao Song — papers of 2023: 2 papers on Elamur Research, the most cited first — what each work is about in our own words."
canonical: "https://research.elamur.ai/free/en/authors/zhao-song/year/2023/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhao-song/year/2023/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Zhao Song](https://md.research.elamur.ai/free/en/authors/zhao-song/) / 2023

# Zhao Song — papers of 2023 — 2 papers, the most cited first

2 papers · [all years of Zhao Song](https://md.research.elamur.ai/free/en/authors/zhao-song/#years)

**[Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://md.research.elamur.ai/free/en/papers/liu-2023-deja-vu-contextual-sparsity-efficient/) [International Conference on Machine Learning (ICML)](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/)**Zichang Liu, Jue Wang, Tri Dao, et al.*2023 · 185 citations*

- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models arXiv:2306.14048](https://md.research.elamur.ai/free/en/papers/zhang-2023-h-2-o-heavy-hitter/) — Zhenyu Zhang, Ying Sheng, Tianyi Zhou, et al. · 2023 · 124 citations