Elamur Research⌕
☰
home / authors / Kaifeng Lyu

Kaifeng Lyu

Kaifeng Lyu has 3 papers in our library, in 2024, most of them on Information retrieval & search, Bias, fairness & safety; often with Anirudh Goyal, Ashwinee Panda, Jiatong Yu.

3 papers in our library · 2024

OpenAlex · h-index 6 · 27 works · 253 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 133 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7678

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

🎓Tsinghua UniversityBeijing · China2018–2026 · 7 paperscurrent🎓Princeton UniversityPrinceton · United States2021–2024 · 10 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).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksSafety Research · 1 workSocial Sciences · 1 workInformation Systems · 1 work

🧭 Topics 2Research subjects and languages the work is about.Bias, fairness & safety · 1 workInformation retrieval & search · 1 work

 Works by year

2020s

20243 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Safety Alignment Should Be Made More Than Just a Few Tokens Deep (2024 · 97 citations)
    The paper asks why safety-aligned LLMs are so easy to break, whether through adversarial suffixes, prefilling, tweaked decoding parameters, or a few steps of fine-tuning.
  2. AI-Assisted Generation of Difficult Math Questions (2024 · 23 citations)
    LLM training now treats mathematical reasoning as a core capability, but public sources of hard problems are largely used up.
  3. RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval (2024 · 17 citations)
    The paper asks whether memory-efficient recurrent models such as Mamba, RWKV and Linear Transformers can match the expressive power of softmax-attention Transformers on algorithmic tasks, particularly when both use Chain-of-Thought (CoT).

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Safety Alignment Should Be Made More Than Just a Few Tokens DeeparXiv:2406.05946Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, et al.2024 · 97 citations
  2. AI-Assisted Generation of Difficult Math QuestionsarXiv:2407.21009Vedant Shah, Dingli Yu, Kaifeng Lyu, et al.2024 · 23 citations
  3. RNNs are not Transformers (Yet): The Key Bottleneck on In-context RetrievalarXiv:2402.18510Kaiyue Wen, Xingyu Dang, Kaifeng Lyu2024 · 17 citations
  4. Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization ↗arXiv (Cornell University) · no summary yetKaiyue Wen et al.2026 · 2 citations

 Co-authors here

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

 Cited by

Papers of our library cite their works 133 times (of the 149,439 papers whose bibliographies we read); 44 citing papers with a page here →.

Updated

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