Elamur Research⌕
☰
home / authors / Xinyi Le

Xinyi Le

Xinyi Le has 2 papers in our library, in 2025–2026, most of them on Reasoning; often with Chenrui Cao, Dacheng Tao, Fan Yang.

2 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 26 · 103 works · 2,958 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 12 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #12439

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

🎓Shanghai Jiao Tong UniversityShanghai · China2016–2026 · 83 papersEmploymentcurrent🎓Chinese University of Hong KongHong Kong · China2013–2016 · 16 papers🏛️Ministry of Education of the People's Republic of ChinaBeijing · China2021–2022 · 5 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 4The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksComputational Theory and Mathematics · 1 workComputer Vision and Pattern Recognition · 1 work

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1 work

 Works by year

2020s

20261 paper20251 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models (2025 · 7 citations)
    The paper asks whether formal theorem proving in Lean 4 really requires costly RL-trained prover models. The authors return to the older Draft, Sketch and Prove (DSP) pipeline and rebuild it as DSP+, which needs no training or fine-tuning. Each stage combines neural and rule-based components:
  2. RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents (2026)
    Mixture-of-Agents (MoA) setups let several LLMs refine each other's answers over multiple layers. Because every model runs at every layer, this is expensive and slow. Sparse MoA adds an LLM judge to filter answers, but all models still have to generate before the judge sees them. Neither approach scales well to pools…

All works

3 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. Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYuchao Wang et al.2022 · 509 citations
  2. Reviving DSP for Advanced Theorem Proving in the Era of Reasoning ModelsConference on Neural Information Processing Systems (NeurIPS)Chenrui Cao, Liangcheng Song, Zenan Li, et al.2025 · 7 citations
  3. RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-AgentsAnnual Meeting of the Association for Computational Linguistics (ACL)Jize Wang, Han Wu, Zhiyuan You, et al.2026

 Co-authors here

9 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 12 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/xinyi-le/