Elamur Research⌕
☰
home / authors / Shu Liu

Shu Liu

Shu Liu has 4 papers in our library, in 2023–2025, most of them on Language models & pretraining, Reasoning, Evaluation & benchmarks; often with Dacheng Li, Ion Gabriel Stoica, Joseph E. Gonzalez.

4 papers in our library · 2023–2025

OpenAlex · ORCID · Wikidata · h-index 5 · 19 works · 67 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 187 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #6944

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

🏛️Chinese Academy of SciencesBeijing · China2021–2025 · 3 paperscurrent🎓Chongqing University of Arts and SciencesChongqing · China2025–2026 · 2 paperscurrent🔬National Astronomical ObservatoriesBeijing · China2021–2025 · 3 papers🎓University of California, BerkeleyBerkeley · United States2025 · 3 papers🔬Beijing Proteome Research CenterBeijing · China2019–2022 · 3 papers🔬State Key Laboratory of ProteomicsBeijing2019–2022 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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 7The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArtificial Intelligence · 4 worksArts and Humanities · 3 worksLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 2 worksInformation Systems · 1 workHardware and Architecture · 1 work

🧭 Topics 4Research subjects and languages the work is about.Language models & pretraining · 2 worksReasoning · 2 worksGPU & parallel computing · 1 workEvaluation & benchmarks · 1 work

 Works by year

2020s

20252 papers20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! (2025 · 56 citations)
    Large reasoning models solve hard problems through long chains of thought with self-checking and backtracking.
  2. MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs (2024 · 51 citations)
    Mixture-of-Experts LLMs keep per-token compute low but need very large amounts of memory. The expert FFNs of Mixtral 8x22B alone take more than 256 GB. This paper targets offline, throughput-oriented batch inference, such as model evaluation, synthetic data generation and data wrangling, when the GPU cannot hold the…
  3. The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks (2025 · 41 citations)
    Large Reasoning Models (LRMs) such as o1, QwQ and DeepSeek-R1 perform well on static benchmarks. In agentic settings, however, they must keep choosing between acting in the environment and continuing to reason internally. The authors call this the Reasoning-Action Dilemma. They study "overthinking," where a model…
  4. MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation (2023 · 36 citations)
    Math word-problem benchmarks such as GSM8K are close to saturation. Leading LLMs exceed 80% accuracy, scoring checks only the final answer, and test-set contamination may inflate results. The authors propose testing models as graders instead of solvers, a setup they call meta-reasoning. They built MR-GSM8K from three…

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!arXiv:2502.07374Dacheng Li, Shiyi Cao, Tyler Griggs, et al.2025 · 56 citations
  2. MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUsASPLOS 2025Shiyi Cao, Shu Liu, Tyler Griggs, et al.2024 · 51 citations
  3. The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic TasksarXiv:2502.08235Alejandro Cuadron, Dacheng Li, Wenjie Ma, et al.2025 · 41 citations
  4. MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model EvaluationarXiv:2312.17080Zhongshen Zeng, Pengguang Chen, Shu Liu, et al.2023 · 36 citations
  5. Language Models Can Easily Learn to Reason from Demonstrations ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetDacheng Li et al.2025 · 14 citations

 Co-authors here

12 of 18 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 187 times (of the 149,439 papers whose bibliographies we read); 49 citing papers with a page here →.

Updated

↑ back to top

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