Elamur Research⌕
☰
home / authors / Deyu Zhou

Deyu Zhou

Deyu Zhou has 9 papers in our library, in 2025–2026, most of them on Reasoning, Language models & pretraining, Dialogue systems; often with Jialong Wu, Linhai Zhang, Yulan He.

9 papers in our library · 2025–2026

OpenAlex · h-index 1 · 9 works · 1 citations OpenAlex, 2026-10-14

📄 9 works in our library · 🔗 Cited 78 times in our library · ⭐ Paper Stars ranking: #7993

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

🎓Southeast UniversityNanjing · China2026 · 8 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 8The field of science this work belongs to (OpenAlex fields).Computer Science · 9 worksArts and Humanities · 8 worksArtificial Intelligence · 8 worksLanguage and Linguistics · 8 worksInformation Systems · 4 worksComputer Vision and Pattern Recognition · 1 workLiterature and Literary Theory · 1 workSoftware · 1 work

🧭 Topics 4Research subjects and languages the work is about.Reasoning · 3 worksLanguage models & pretraining · 2 worksDialogue systems · 1 workInformation retrieval & search · 1 work

💡 Concepts 2Key ideas and methods explained on our concept pages.Inverted index · 1 workArtificial intelligence · 1 work

 Works by year

2020s

20265 papers20254 papers

 Papers

The most cited first (OpenAlex and our library).

  1. WebWalker: Benchmarking LLMs in Web Traversal (2025 · 72 citations)
    Search-engine retrieval in standard RAG pipelines tends to return surface-level pages. Answers buried several clicks deep inside a website are often missed. The authors call this problem Web Traversal: starting from a site's root URL, an agent must click through subpages to find the information a query needs. To…
  2. AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment (2025 · 9 citations)
    Conversational search needs to turn a context-dependent user question, often with omissions, coreference or ambiguity, into a self-contained query that standard retrievers can handle.
  3. SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding (2025 · 8 citations)
    Tree-search-based (TSB) reasoning methods such as Tree-of-Thoughts (ToT) help LLMs plan and reason. However, they are slow because many thoughts must be generated and scored before the tree can grow. Earlier work sped up the search algorithms. This paper targets tree construction itself with SEED, a training-free…
  4. PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation (2025 · 6 citations)
    Personalizing large language models by fine-tuning separate parameters for each user is limited because most users supply very little data.
  5. Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning (2026 · 1 citation)
    The paper addresses a gap in LLM meta-reasoning. Most current approaches are episodic: they plan or intervene within one problem and then discard what they learned. As a result, the same mistakes recur and the costly verification and retry routines run again from scratch. The authors propose Metacognitive…
  6. Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties (2026)
    Existing temporal reasoning benchmarks for LLMs are mostly English and rule-generated. They offer little narrative context and test few entities at a time. The authors address this with Chinese Time Reasoning (CTM), a Chinese-language benchmark based on dynastic chronology from roughly 2100 BCE to 1912. It draws on a…
  7. Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation (2026)
    Most claim detection benchmarks treat claims as fixed sentences, either mined from sources such as political debates or filled into LLM templates.
  8. Let the Comments Speak: A Multi-Agent Framework based on Large Language Model for Comment-Guided Code Refactoring (2026)
    LLM-based refactoring tools tend to treat code mostly as syntax and ignore the intent that comments convey.
  9. MA²P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion (2026)
    The paper addresses complex persuasive dialogue, where the persuadee's beliefs and desires are hidden and must be inferred.

 Co-authors here

12 of 18 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 78 times (of the 149,439 papers whose bibliographies we read); 38 citing papers with a page here →.

Updated

↑ back to top

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