--- title: "Xinyi Le — author profile and papers — Elamur Research" description: "Xinyi Le, Shanghai Jiao Tong University: 2 papers on Elamur Research (2025–2026), h-index 26 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/xinyi-le/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xinyi-le/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xinyi Le # Xinyi Le Xinyi Le has 2 papers in our library, in 2025–2026, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Chenrui Cao](https://md.research.elamur.ai/free/en/authors/chenrui-cao/), [Dacheng Tao](https://md.research.elamur.ai/free/en/authors/dacheng-tao/), [Fan Yang](https://md.research.elamur.ai/free/en/authors/fan-yang/). 2 papers in our library · 2025–2026 [OpenAlex](https://openalex.org/A5052481491) · [ORCID](https://orcid.org/0000-0003-0318-9497) · [**h-index 26**](https://openalex.org/authors/A5052481491) · [103 works](https://openalex.org/works?filter=author.id:A5052481491) · [2,958 citations](https://openalex.org/works?filter=author.id:A5052481491&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/xinyi-le/#papers) · [🔗 Cited 12 times in our library](https://md.research.elamur.ai/free/en/authors/xinyi-le/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #12439](https://md.research.elamur.ai/free/en/paper-stars/page/125/#star-12439) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Xinyi+Le) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xinyi+Le) · [dblp](https://dblp.org/search?q=Xinyi+Le) · [ACL Anthology](https://aclanthology.org/search/?q=Xinyi+Le) ## Affiliations [🎓**Shanghai Jiao Tong University** Shanghai · China 2016–2026 · 83 papersEmployment*current*](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) · [🎓**Chinese University of Hong Kong** Hong Kong · China 2013–2016 · 16 papers](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) · [🏛️**Ministry of Education of the People's Republic of China** Beijing · China 2021–2022 · 5 papers](https://md.research.elamur.ai/free/en/government/ministry-of-education-of-the-people-s-republic-of-china/) 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 4 The field of science this work belongs to (OpenAlex fields).[Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) 🧭 Topics 1 Research subjects and languages the work is about.[Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2020s [**2026** 1 paper](https://md.research.elamur.ai/free/en/authors/xinyi-le/year/2026/) · [**2025** 1 paper](https://md.research.elamur.ai/free/en/authors/xinyi-le/year/2025/) ## Papers The most cited first (OpenAlex and our library). 1. **[Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models](https://md.research.elamur.ai/free/en/papers/cao-2025-reviving-dsp-advanced-theorem-proving/)** *(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](https://md.research.elamur.ai/free/en/papers/wang-2026-routemoa-dynamic-routing-without-pre/)** *(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 ↗](https://doi.org/10.1109/cvpr52688.2022.00421) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Yuchao Wang et al.*2022 · 509 citations* 2. **[Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models](https://md.research.elamur.ai/free/en/papers/cao-2025-reviving-dsp-advanced-theorem-proving/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Chenrui Cao, Liangcheng Song, Zenan Li, et al.*2025 · 7 citations* 3. **[RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents](https://md.research.elamur.ai/free/en/papers/wang-2026-routemoa-dynamic-routing-without-pre/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jize Wang, Han Wu, Zhiyuan You, et al.*2026* ## Co-authors here 9 co-authors with a page, the most papers together first. - [Chenrui Cao](https://md.research.elamur.ai/free/en/authors/chenrui-cao/) - [Dacheng Tao](https://md.research.elamur.ai/free/en/authors/dacheng-tao/) - [Fan Yang](https://md.research.elamur.ai/free/en/authors/fan-yang/) - [Hui Xue](https://md.research.elamur.ai/free/en/authors/hui-xue/) - [Songyang Zhang](https://md.research.elamur.ai/free/en/authors/songyang-zhang/) - [Xian Zhang](https://md.research.elamur.ai/free/en/authors/xian-zhang/) - [Yining Li](https://md.research.elamur.ai/free/en/authors/yining-li/) - [Zenan Li](https://md.research.elamur.ai/free/en/authors/zenan-li/) - [Zifei Shan](https://md.research.elamur.ai/free/en/authors/zifei-shan/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/): [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2025](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/) - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ## 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 →](https://md.research.elamur.ai/free/en/authors/xinyi-le/cited-by/). Updated 4 November 2026