Elamur Research⌕
☰
home / authors / Xingyu Dang

Xingyu Dang

Xingyu Dang has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Reasoning, Information retrieval & search; often with Kaiyue Wen, Aditi Raghunathan, Kaifeng Lyu.

2 papers in our library · 2024–2025

OpenAlex · h-index 1 · 7 works · 1 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 30 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #10652

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

🎓Princeton UniversityPrinceton · United States2026 · 5 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 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).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 3Research subjects and languages the work is about.Information retrieval & search · 1 workLanguage models & pretraining · 1 workReasoning · 1 work

 Works by year

2020s

20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. 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).
  2. Weight Ensembling Improves Reasoning in Language Models (2025 · 10 citations)
    When reasoning models are trained with supervised finetuning (SFT), the variety of their outputs shrinks. Pass@1 keeps rising, but Pass@k peaks early and then falls, which weakens test-time scaling methods such as majority voting or reranking with a reward model. The authors finetune Gemma-2-2B and Qwen-2.5-0.5B on…

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. RNNs are not Transformers (Yet): The Key Bottleneck on In-context RetrievalarXiv:2402.18510Kaiyue Wen, Xingyu Dang, Kaifeng Lyu2024 · 17 citations
  2. Weight Ensembling Improves Reasoning in Language ModelsarXiv:2504.10478 · COLM 2025Xingyu Dang, Christina Baek, Kaiyue Wen, et al.2025 · 10 citations
  3. Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement ↗arXiv:2606.06468 · no summary yetJui-Hui Chung et al.2026 · 2 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

4 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 30 times (of the 149,439 papers whose bibliographies we read); 6 citing papers with a page here →.

Updated

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