Elamur Research⌕
☰
home / authors / Yu Xia

Yu Xia

Yu Xia has 9 papers in our library, in 2021–2026, most of them on Language models & pretraining, Vision & language, Question answering; often with Tong Yu, Julian McAuley, Junda Wu.

9 papers in our library · 2021–2026

OpenAlex · ORCID · h-index 16 · 98 works · 2,575 citations OpenAlex, 2026-10-14

📄 9 works in our library · 🔗 Cited 68 times in our library · ⭐ Paper Stars ranking: #6419

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

🏥First Affiliated Hospital Zhejiang UniversityHangzhou · China2026 · 2 paperscurrent🔬State Key Laboratory of Diagnosis and Treatment of Infectious DiseasesHangzhou2026 · 2 paperscurrent🎓Zhejiang UniversityHangzhou · China2026 · 2 paperscurrent🏢Alibaba GroupHangzhou · China2026 · 1 papercurrent🎓Nanjing Sport InstituteNanjing · China2026 · 1 papercurrent🎓Pennsylvania State UniversityState College · United States2008–2024 · 18 papers🎓University of MinnesotaMinneapolis · United States2007–2012 · 13 papers🎓Emporia State UniversityEmporia · United States2022–2025 · 9 papers🎓Huazhong Agricultural UniversityWuhan · China2004–2025 · 4 papers🔬NARI GroupNanjing · China2019–2024 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 27 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 10The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 9 worksComputer Science · 9 worksArtificial Intelligence · 9 worksLanguage and Linguistics · 9 worksComputer Vision and Pattern Recognition · 4 worksInformation Systems · 5 worksSocial Sciences · 1 workSociology and Political Science · 1 workDecision Sciences · 1 workManagement Science and Operations Research · 1 work

🧭 Topics 7Research subjects and languages the work is about.Language models & pretraining · 4 worksEnglish · 1 workVision & language · 2 worksReasoning · 1 workQuestion answering · 1 workInformation retrieval & search · 1 workDialogue systems · 1 work

 Works by year

2020s

20263 papers20254 papers20241 paper20211 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English (2021 · 44 citations)
    The paper describes the third-place system in the Constraint@AAAI 2021 shared task. The task was binary classification of English social-media posts about COVID-19 (from Twitter, Facebook, Instagram and similar sources) as fake or real. The authors trained on the official dataset plus extra data they gathered online.…
  2. A Survey of Small Language Models (2024 · 31 citations)
    Large language models perform well but need heavy compute, memory and data, so they usually run on centralized, specialized hardware.
  3. From Selection to Generation: A Survey of LLM-based Active Learning (2025 · 22 citations)
    Active learning (AL) traditionally lowers labeling effort by picking the most useful unlabeled examples with metrics such as uncertainty or diversity.
  4. Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs (2025 · 19 citations)
    Chain-of-Thought (CoT) prompting showed that LLMs reason better when they write out intermediate steps before giving an answer.
  5. Doc-React: Multi-page Heterogeneous Document Question-answering (2025 · 6 citations)
    Doc-React tackles question answering over long documents whose pages mix text, charts and images in irregular layouts.
  6. Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models (2025 · 5 citations)
    Retrieval-augmented LLMs do not always benefit from external documents. When a model already knows the answer, retrieval adds cost and latency and can even hurt quality. Adaptive RAG (ARAG) tries to retrieve only when needed. Earlier ARAG methods either count entity frequencies in the pre-training corpus, which is…
  7. LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization (2026 · 3 citations)
    GUI agents built on multimodal LLMs often click or point at the wrong spot. Supervised Fine-Tuning (SFT) handles coordinates poorly. Earlier reinforcement-learning approaches judge location coarsely, using text matching, fixed IoU thresholds, or rigid decision boundaries. UI-TARS-style DPO also needs hand-built…
  8. A Survey on LLM-based Conversational User Simulation (2026 · 1 citation)
    This survey organizes the fast-growing literature on using large language models to imitate users in dialogue.
  9. CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing (2026)
    The paper addresses indirect prompt injection, where an LLM obeys commands hidden inside supplied context (e.g., a retrieved passage) instead of answering the user's actual request.

 Co-authors here

12 of 41 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 68 times (of the 149,439 papers whose bibliographies we read); 15 citing papers with a page here →.

Updated

↑ back to top

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