Elamur Research⌕
☰
home / authors / Zhao Song

Zhao Song

Zhao Song has 2 papers in our library, in 2023, most of them on Language models & pretraining; often with Christopher Ré, Tianyi Zhou, Yuandong Tian.

2 papers in our library · 2023

OpenAlex · ORCID · h-index 9 · 31 works · 276 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 289 times in our library · ⭐ Paper Stars ranking: #5471

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Kunming University of Science and TechnologyKunming · China2026 · 1 papercurrent🏛️Chinese Academy of SciencesBeijing · China2011–2025 · 10 papers🎓Zhengzhou University of AeronauticsZhengzhou · China2008–2024 · 10 papers🔬Shenzhen Institutes of Advanced TechnologyShenzhen · China2018–2025 · 6 papers🎓University of Chinese Academy of SciencesBeijing · China2012–2020 · 6 papers🎓Chinese University of Hong KongHong Kong · China2018–2025 · 5 papers🔬Institute of Coal ChemistryTaiyuan · China2012–2013 · 2 papers🎓Naval University of EngineeringWuhan · China2010 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksArts and Humanities · 1 workComputer Vision and Pattern Recognition · 1 workLanguage and Linguistics · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 2 works

 Works by year

2020s

20232 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time (2023 · 185 citations)
    Serving very large language models is slow, especially when generating tokens one at a time in latency-sensitive settings.
  2. H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models (2023 · 124 citations)
    Serving large language models is costly partly because of the KV cache. This is the stored attention keys and values, and it grows linearly with batch size and sequence length. A 30B model with batch 128 and 1024-token sequences already needs about 180GB. The authors look for a way to cap this cache without hurting…

 Co-authors here

12 of 14 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 289 times (of the 149,439 papers whose bibliographies we read); 45 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhao-song/