---
title: "Xiang Wang — author profile and papers — Elamur Research"
description: "Xiang Wang, University of Science and Technology of China: 7 papers on Elamur Research (2025–2026), h-index 51 — affiliations, topics…"
canonical: "https://research.elamur.ai/free/en/authors/xiang-wang/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xiang-wang/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xiang Wang

# Xiang Wang

Xiang Wang has 7 papers in our library, in 2025–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/); often with [An Zhang](https://md.research.elamur.ai/free/en/authors/an-zhang/), [Junfeng Fang](https://md.research.elamur.ai/free/en/authors/junfeng-fang/), [Sihang Li](https://md.research.elamur.ai/free/en/authors/sihang-li/).

7 papers in our library · 2025–2026

[OpenAlex](https://openalex.org/A5100389037) · [ORCID](https://orcid.org/0000-0002-6148-6329) · [Wikidata](https://www.wikidata.org/wiki/Q130800750) · [**h-index 51**](https://openalex.org/authors/A5100389037) · [277 works](https://openalex.org/works?filter=author.id:A5100389037) · [18,639 citations](https://openalex.org/works?filter=author.id:A5100389037&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 7 works in our library](https://md.research.elamur.ai/free/en/authors/xiang-wang/#papers) · [🔗 Cited 111 times in our library](https://md.research.elamur.ai/free/en/authors/xiang-wang/cited-by/) · [4 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #6536](https://md.research.elamur.ai/free/en/paper-stars/page/66/#star-6536)

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=Xiang+Wang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xiang+Wang) · [dblp](https://dblp.org/search?q=Xiang+Wang) · [ACL Anthology](https://aclanthology.org/search/?q=Xiang+Wang)

## Affiliations

[🎓**University of Science and Technology of China** Hefei · China 2010–2026 · 106 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) · [🎓**National University of Defense Technology** Changsha · China 2014–2026 · 9 papers*current*](https://md.research.elamur.ai/free/en/universities/national-university-of-defense-technology/) · [🎓**Huazhong University of Science and Technology** Wuhan · China 2022–2026 · 8 papers*current*](https://md.research.elamur.ai/free/en/universities/huazhong-university-of-science-and-technology/) · [🎓**Central South University** Changsha · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/central-south-university/) · [🎓**China University of Petroleum, East China** Qingdao · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/china-university-of-petroleum-east-china/) · [🎓**National University of Singapore** Singapore · Singapore 2014–2025 · 43 papersEmployment since 2014 · Research Fellow, School of Computing](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) · [🎓**Zhengzhou University of Aeronautics** Zhengzhou · China 2023–2025 · 4 papers](https://ror.org/01qjyzh50) · [🔬**IBM Research - Thomas J. Watson Research Center** Yorktown Heights · United States 2013–2014 · 4 papers](https://md.research.elamur.ai/free/en/labs/ibm-research-thomas-j-watson-research-center/) · [🎓**Beihang University** Beijing · China 2021–2025 · 3 papers](https://md.research.elamur.ai/free/en/universities/beihang-university/) · [🎓**Hefei University of Technology** Hefei · China 2022–2025 · 3 papers](https://md.research.elamur.ai/free/en/universities/hefei-university-of-technology/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 43 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 7 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 7 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 7 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 7 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 7 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Signal Processing · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/)

🧭 Topics 4 Research subjects and languages the work is about.[Language models & pretraining · 3 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Dialogue systems · 1 work](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Information retrieval & search · 1 work](https://md.research.elamur.ai/free/en/topics/information-retrieval/)

## Works by year

### 2020s

[**2026** 2 papers](https://md.research.elamur.ai/free/en/authors/xiang-wang/year/2026/) · [**2025** 5 papers](https://md.research.elamur.ai/free/en/authors/xiang-wang/year/2025/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://md.research.elamur.ai/free/en/papers/li-2025-hello-again-llm-powered-personalized/)** *(2025 · 55 citations)* Most open-domain chatbots are built for short, single-session exchanges. Real companionship, however, requires remembering past conversations and keeping track of who the user and the bot are. The authors present LD-Agent, a model-agnostic framework that splits long-term dialogue into three separately trainable…
2. **[START: Self-taught Reasoner with Tools](https://md.research.elamur.ai/free/en/papers/li-2025-start-self-taught-reasoner-tools/)** *(2025 · 21 citations)* Large Reasoning Models (LRMs) handle multi-step reasoning well but often make mistakes in exact arithmetic, enumeration and algorithmic steps.
3. **[Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning](https://md.research.elamur.ai/free/en/papers/shi-2025-search-refine-during-think-facilitating/)** *(2025 · 18 citations)* Retrieval-augmented LLMs trained with reinforcement learning tend to reason over whole retrieved documents, which are often noisy.
4. **[Neuron-Level Sequential Editing for Large Language Models](https://md.research.elamur.ai/free/en/papers/jiang-2025-neuron-level-sequential-editing-large/)** *(2025 · 15 citations)* Large language models store facts that go out of date, and full retraining is expensive. Parameter-editing methods such as ROME and MEMIT work well for a single round of edits. When edits are applied one after another, however, they tend to lose earlier edits ("model forgetting") and can collapse into incoherent…
5. **[Route Sparse Autoencoder to Interpret Large Language Models](https://md.research.elamur.ai/free/en/papers/shi-2025-route-sparse-autoencoder-interpret-large/)** *(2025 · 11 citations)* Sparse autoencoders (SAEs) are a popular way to break LLM activations into interpretable, mostly monosemantic features.
6. **[SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs](https://md.research.elamur.ai/free/en/papers/sun-2026-sepseq-training-free-framework-long/)** *(2026 · 1 citation)* Modern LLMs advertise very long context windows, yet they handle long sequences of numbers poorly. Tasks such as counting, filtering, or spotting trends need exact access to every value. The authors trace this failure to attention dispersion: as inputs grow, Softmax spreads attention over many similar numeric tokens…
7. **[FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow Generation](https://md.research.elamur.ai/free/en/papers/wang-2026-fusionflow-enabling-deep-structural-exploration/)** *(2026)* Automated generators of agentic workflows, such as ADAS and AFlow, usually improve one evolving workflow through small local edits or tree search.

## All works

11 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. **[LightGCN ↗](https://doi.org/10.1145/3397271.3401063) International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · no summary yet**Xiangnan He et al.*2020 · 4,432 citations*
2. **[Explainable Reasoning over Knowledge Graphs for Recommendation ↗](https://doi.org/10.1609/aaai.v33i01.33015329) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Xiang Wang et al.*2019 · 770 citations*
3. **[Smart Contract Vulnerability Detection using Graph Neural Network ↗](https://doi.org/10.24963/ijcai.2020/454) International Joint Conference on Artificial Intelligence · no summary yet**Yuan Zhuang et al.*2020 · 405 citations*
4. **[Micro Tells Macro ↗](https://doi.org/10.1145/2964284.2964314) ACM International Conference on Multimedia (ACM MM) · no summary yet**Jingyuan Chen et al.*2016 · 160 citations*
5. **[Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://md.research.elamur.ai/free/en/papers/li-2025-hello-again-llm-powered-personalized/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Hao Li, Chenghao Yang, An Zhang, et al.*2025 · 55 citations*
6. **[START: Self-taught Reasoner with Tools](https://md.research.elamur.ai/free/en/papers/li-2025-start-self-taught-reasoner-tools/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Chengpeng Li, Mingfeng Xue, Zhenru Zhang, et al.*2025 · 21 citations*
7. **[Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning](https://md.research.elamur.ai/free/en/papers/shi-2025-search-refine-during-think-facilitating/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Yaorui Shi, Sihang Li, Chang Wu, et al.*2025 · 18 citations*
8. **[Neuron-Level Sequential Editing for Large Language Models](https://md.research.elamur.ai/free/en/papers/jiang-2025-neuron-level-sequential-editing-large/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Houcheng Jiang, Junfeng Fang, Tianyu Zhang, et al.*2025 · 15 citations*
9. **[Route Sparse Autoencoder to Interpret Large Language Models](https://md.research.elamur.ai/free/en/papers/shi-2025-route-sparse-autoencoder-interpret-large/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Wei Shi, Sihang Li, Tao Liang, et al.*2025 · 11 citations*
10. **[SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs](https://md.research.elamur.ai/free/en/papers/sun-2026-sepseq-training-free-framework-long/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jie Sun, Yu Liu, Lu Han, et al.*2026 · 1 citation*
11. **[FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow Generation](https://md.research.elamur.ai/free/en/papers/wang-2026-fusionflow-enabling-deep-structural-exploration/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiang Wang, Zongtao Yang, Zhuojian Hong, et al.*2026*

## Co-authors here

12 of 30 co-authors with a page, the most papers together first.

- [An Zhang](https://md.research.elamur.ai/free/en/authors/an-zhang/) ×3
- [Junfeng Fang](https://md.research.elamur.ai/free/en/authors/junfeng-fang/) ×2
- [Sihang Li](https://md.research.elamur.ai/free/en/authors/sihang-li/) ×2
- [Tao Liang](https://md.research.elamur.ai/free/en/authors/tao-liang/) ×2
- [Baolong Bi](https://md.research.elamur.ai/free/en/authors/baolong-bi/)
- [Beichen Zhang](https://md.research.elamur.ai/free/en/authors/beichen-zhang/)
- [Binyuan Hui](https://md.research.elamur.ai/free/en/authors/binyuan-hui/)
- [Bowen Yu](https://md.research.elamur.ai/free/en/authors/bowen-yu/)
- [Chenghao Yang](https://md.research.elamur.ai/free/en/authors/chenghao-yang/)
- [Chengpeng Li](https://md.research.elamur.ai/free/en/authors/chengpeng-li/)
- [Dayiheng Liu](https://md.research.elamur.ai/free/en/authors/dayiheng-liu/)
- [Hao Li](https://md.research.elamur.ai/free/en/authors/hao-li/)

## 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/) ×2: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/), [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)
- [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ×2: [EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/) ×2
- [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/): [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)
- [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/): [NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/)
- [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/)
- ACM International Conference on Multimedia (ACM MM)
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
- International Joint Conference on Artificial Intelligence
- Proceedings of the AAAI Conference on Artificial Intelligence

## Cited by

Papers of our library cite their works 111 times (of the 149,439 papers whose bibliographies we read); [27 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/xiang-wang/cited-by/).

Updated 1 November 2026