Elamur Research⌕
☰
home / authors / Fangcheng Liu

Fangcheng Liu

Fangcheng Liu has 4 papers in our library, in 2023–2025, most of them on Language models & pretraining; often with Yehui Tang, Kai Han, Hang Zhou.

4 papers in our library · 2023–2025

OpenAlex · h-index 1 · 1 works · 1 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 28 times in our library · ⭐ Paper Stars ranking: #8454

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

 Fields, topics and concepts

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

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArtificial Intelligence · 4 worksArts and Humanities · 3 worksComputer Vision and Pattern Recognition · 3 worksLanguage and Linguistics · 3 worksHardware and Architecture · 2 works

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

 Works by year

2020s

20252 papers20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. PanGu-π: Enhancing Language Model Architectures via Nonlinearity Compensation (2023 · 10 citations)
    Progress in large language models has mostly come from adding parameters and data. The design of the Transformer block itself gets little attention, even though large models are costly to run. The authors study LLaMA-style decoders and identify feature collapse: a rank metric shows token representations growing more…
  2. Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs (2025 · 8 citations)
    Training MoE language models with nearly a trillion parameters is hard: the hardware is underused because the set of experts each token activates changes at runtime, and the scale strains communication and memory.
  3. PanGu-π Pro:Rethinking Optimization and Architecture for Tiny Language Models (2024 · 8 citations)
    On-device deployment needs small language models that still perform well. Most tiny models, however, simply reuse recipes designed for much larger LLMs, and few studies test which of those choices actually suit a ~1B-parameter model. The authors run a systematic set of ablations on a 1B LLaMA-style baseline, trained…
  4. Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity (2025 · 4 citations)
    Sparse Mixture-of-Experts LLMs are cheap per token. However, when experts are spread across accelerators, uneven routing overloads some devices, and the slowest device limits overall speed. The Pangu Team at Huawei proposes Mixture of Grouped Experts (MoGE). Experts are split into equal, non-overlapping groups…

 Co-authors here

12 of 17 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 28 times (of the 149,439 papers whose bibliographies we read); 4 citing papers with a page here →.

Updated

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