Elamur Research⌕
☰
home / authors / Zirui Liu

Zirui Liu

Zirui Liu has 3 papers in our library, in 2024, most of them on Language models & pretraining, Low-resource languages, Efficient models & compression; often with Hongye Jin, Xia Hu, Beidi Chen.

3 papers in our library · 2024

OpenAlex · ORCID · Wikidata · h-index 24 · 141 works · 2,465 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 355 citations in our library · ⭐ Paper Star rank #3679

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

🎓Peking UniversityBeijing · China2021–2026 · 21 paperscurrent🎓University of MinnesotaMinneapolis · United States2024–2026 · 11 paperscurrent🎓Chongqing UniversityChongqing · China2019–2026 · 4 paperscurrent🎓Fuzhou UniversityFuzhou · China2026 · 1 papercurrent🎓New York UniversityNew York · United States2026 · 1 papercurrent🎓Rice UniversityHouston · United States2021–2024 · 15 papers🎓Jilin UniversityChangchun · China2024–2025 · 8 papers🎓University of California, Los AngelesLos Angeles · United States2017–2022 · 7 papers🎓Princeton UniversityPrinceton · United States2018–2021 · 6 papers🎓Texas A&M UniversityCollege Station · United States2020–2024 · 5 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 31 more institutions on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 6 Arts and Humanities · 3 works Computer Science · 3 works Artificial Intelligence · 3 works Language and Linguistics · 3 works Computer Vision and Pattern Recognition · 1 work Hardware and Architecture · 1 work

🧭 Topics 3 Efficient models & compression · 1 work Language models & pretraining · 2 works Low-resource languages · 1 work

 Works by year

2020s

20243 papers

 Papers

The most cited first (OpenAlex and our library).

  1. KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache (2024 · 243 citations)
    Serving LLMs cheaply means batching many requests. With large batches and long contexts, though, the KV cache becomes the main memory and speed bottleneck: it can exceed the size of the model weights, and the GPU must read it in full for every generated token. The authors examine how values are distributed inside the…
  2. Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages (2024 · 95 citations)
    LLMs are trained on corpora dominated by English. For example, about 92.65% of GPT-3 tokens and 89.7% of LlaMa2 pre-training data are English. As a result, low-resource languages get weaker support, yet there are few quantitative ways to measure this gap. The authors propose Language Ranker, an intrinsic metric that…
  3. LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning (2024 · 78 citations)
    Large language models that use RoPE usually fail on inputs longer than their pretraining sequence length. Perplexity spikes and outputs become erratic. In this ICML 2024 paper, the authors argue that the problem is not a lack of long-text understanding. Instead, they blame a "positional O.O.D." effect: at inference…

 Co-authors here

10 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 355 times (of the 141,840 papers whose bibliographies we read); 17 citing papers with a page here →.

Updated

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