🧑‍🔬 Fei Qing Wu

🏛️ Affiliations

🎓Zhejiang UniversityHangzhou · China2002–2026 · 527 papersEducation since 2010 · Ph. D/ Professor, College of Computer Sciencecurrent🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2022–2026 · 33 paperscurrent🎓Guangdong University of FinanceGuangzhou · China2024–2026 · 3 paperscurrent🎓Shandong UniversityJinan · China2013–2026 · 2 paperscurrent🎓Shanghai University of Engineering ScienceShanghai · China2013–2025 · 23 papers🎓Pennsylvania State UniversityState College · United States2005–2019 · 15 papers🎓Peking UniversityBeijing · China2011–2025 · 11 papers🎓University of WashingtonSeattle · United States2007–2010 · 11 papers🏛️Chinese Academy of SciencesBeijing · China2005–2025 · 7 papers🔬Shanghai Advanced Research InstitutePudong · China2022–2023 · 7 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 82 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.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. A Unified MRC Framework for Named Entity Recognition (2020 · 840 citations)
   Standard sequence-labeling NER gives each token exactly one tag, so it cannot represent nested entities, where one token belongs to several overlapping mentions.
2. Dice Loss for Data-imbalanced NLP Tasks (2020 · 735 citations)
   Many NLP tasks are heavily imbalanced: in tagging and machine reading comprehension, background or negative tokens far outnumber positives.
3. Open Information Extraction Using Wikipedia (2010 · 650 citations)
   Most relation extractors are trained on labeled examples for each target relation, so they cannot cover the huge, open-ended variety of relations expressed on the Web.
4. Instruction Tuning for Large Language Models: A Survey (2023 · 520 citations)
   This survey maps the research on instruction tuning (IT), which the authors treat as the same thing as supervised fine-tuning (SFT).
5. GPT-NER: Named Entity Recognition via Large Language Models (2025 · 436 citations)
   Large language models handle many NLP tasks well through in-context learning, but on named entity recognition they have trailed supervised systems.
6. Text Classification via Large Language Models (2023 · 292 citations)
   LLMs prompted through in-context learning still trail fine-tuned classifiers on text classification. The authors attribute this to two causes. First, LLMs reason poorly about linguistic phenomena such as negation, concession, intensification and irony. Second, the context window holds only a few demonstrations. To…
7. CorefQA: Coreference Resolution as Query-based Span Prediction (2020 · 256 citations)
   Most end-to-end coreference systems first propose candidate spans and then score pairs of them. This design has two weaknesses. A mention dropped at the proposal step can never be recovered. Pairs are also compared only through top-layer span vectors, so the surrounding context is barely used. CorefQA treats the task…
8. Learning Dynamic Context Augmentation for Global Entity Linking (2019 · 85 citations)
   Global (collective) entity linking improves disambiguation by enforcing coherence among all entities in a document.
9. Pushing the Limits of ChatGPT on NLP Tasks (2023 · 28 citations)
   When used through in-context prompting, ChatGPT usually lags behind fully supervised models on standard NLP benchmarks.
10. Sentiment Analysis through LLM Negotiations (2023 · 25 citations)
    Large language models are typically applied to sentiment classification through a single in-context learning (ICL) prompt answered in one pass.
11. Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents (2025 · 13 citations)
    LLM agents are increasingly used to role-play learners, for example to test tutoring systems or teaching strategies.
12. Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning (2026 · 11 citations)
    Reinforcement learning with verifiable rewards (RLVR) trains long chain-of-thought models using only a final correct/incorrect signal.
13. InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection (2026 · 10 citations)
    Multimodal-LLM GUI agents often fail to connect an instruction to the right on-screen element or tap location.
14. T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts (2025 · 8 citations)
    Most text-to-image (T2I) evaluation measures prompt alignment, image quality or object composition. It rarely checks whether models depict specific real-world entities correctly, such as a particular handbag model, landmark or dog breed. To fill this gap, the authors built T2I-FactualBench, which they describe as the…
15. DAC-Bench: A Decision-Aware Benchmark for Compositional Mobile GUI Tasks (2026)
    Most mobile GUI benchmarks test short, linear instruction chains and report step-level or overall success. They say little about how LMM-based agents handle long tasks where the next action depends on what appears on screen. DAC-Bench addresses this with compositional tasks built in four steps:
16. Mitigating Structural Knowledge Collapse in Domain-Specific LLMs via Morpheme-Aware KV-Aggregation (2026)
    Subword tokenizers such as BPE often split specialized medical and legal terms (e.g., Hydrochlorothiazide) into pieces that do not match their morphemes.
17. SteuerLLM: Local specialized large language model for German tax law analysis (2026)
    The paper asks whether general-purpose LLMs can handle German tax law. This domain punishes small mistakes: answers must cite the right statutes, follow a structured legal argument, and get the numbers exactly right. The authors make two contributions.
18. Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction (2026)
    Multiple-choice distractors are usually designed for the whole student population, so they miss the specific reasoning errors of individual learners.

All works

36 works of theirs in our library, the most cited first; 18 with a page here, the others link their original until we summarise them.

1. FcaNet: Frequency Channel Attention Networks ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZequn Qin et al.2021 · 1,370 citations
2. Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks ↗International Joint Conference on Artificial Intelligence · no summary yetJun Xiao et al.2017 · 927 citations
3. A Unified MRC Framework for Named Entity RecognitionAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoya Li, Jingrong Feng, Yuxian Meng, et al.2020 · 840 citations
4. Dice Loss for Data-imbalanced NLP TasksAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoya Li, Xiaofei Sun, Yuxian Meng, et al.2020 · 735 citations
5. Open Information Extraction Using WikipediaAnnual Meeting of the Association for Computational Linguistics (ACL)Fei Wu, Daniel S. Weld2010 · 650 citations
6. Instruction Tuning for Large Language Models: A SurveyACM Computing SurveysShengyu Zhang, Linfeng Dong, Xiaoya Li, et al.2023 · 520 citations
7. GPT-NER: Named Entity Recognition via Large Language ModelsFindings of the Association for Computational LinguisticsShuhe Wang, Xiaofei Sun, Xiaoya Li, et al.2025 · 436 citations
8. Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetPingbo Pan et al.2016 · 428 citations
9. Text Classification via Large Language ModelsFindings of the Association for Computational LinguisticsXiaofei Sun, Xiaoya Li, Jiwei Li, et al.2023 · 292 citations
10. Spatio-Temporal Graph Routing for Skeleton-Based Action Recognition ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetBin Li et al.2019 · 264 citations
11. CorefQA: Coreference Resolution as Query-based Span PredictionAnnual Meeting of the Association for Computational Linguistics (ACL)Wei Wu, Fei Wang, Arianna Yuan, et al.2020 · 256 citations
12. ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetZijun Sun et al.2021 · 242 citations
13. BertGCN: Transductive Text Classification by Combining GNN and BERT ↗Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · no summary yetYuxiao Lin et al.2021 · 240 citations
14. De-Biased Court's View Generation with Causality ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetYiquan Wu et al.2020 · 117 citations
15. Judgment Prediction via Injecting Legal Knowledge into Neural Networks ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetLeilei Gan et al.2021 · 86 citations
16. Community-Based Question Answering via Heterogeneous Social Network Learning ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetHanyin Fang et al.2016 · 86 citations
17. Learning Dynamic Context Augmentation for Global Entity LinkingConference on Empirical Methods in Natural Language Processing (EMNLP)Xiyuan Yang, Xiaotao Gu, Sheng Lin, et al.2019 · 85 citations
18. CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetTao Chen et al.2021 · 71 citations
19. Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetYiquan Wu et al.2022 · 61 citations
20. Machine Reading at the University of Washington ↗Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading · no summary yetHoifung Poon et al.2010 · 45 citations
21. ConRPG: Paraphrase Generation using Contexts as Regularizer ↗Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yetYuxian Meng et al.2021 · 36 citations
22. Pushing the Limits of ChatGPT on NLP TasksarXiv:2306.09719Xiaofei Sun, Linfeng Dong, Xiaoya Li, et al.2023 · 28 citations
23. Sentiment Analysis through LLM NegotiationsarXiv:2311.01876Xiaofei Sun, Xiaoya Li, Shengyu Zhang, et al.2023 · 25 citations
24. Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction ↗Findings of the Association for Computational Linguistics: EMNLP 2023 · no summary yetLeilei Gan et al.2023 · 22 citations
25. Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based AgentsAnnual Meeting of the Association for Computational Linguistics (ACL)Tao Wu, Jingyuan Chen, Wang Lin, et al.2025 · 13 citations

See all 36 works by Fei Qing Wu →

🤝 Co-authors here

12 of 39 co-authors with a page, the most papers together first.

• Jiwei Li ×8
• Xiaoya Li ×7
• Xiaofei Sun ×6
• Guoyin Wang ×5
• Tianwei Zhang ×5
• Shengyu Zhang ×4
• Shuhe Wang ×4
• Jingyuan Chen ×2
• Kun Kuang ×2
• Linfeng Dong ×2
• Mengze Li ×2
• Tao Wu ×2

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) ×11: ACL 2026 ×3, ACL 2025 ×2, ACL 2020 ×3, ACL 2010
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×5: EMNLP 2019
• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026, Findings of the Association for Computational Linguistics 2025, Findings of the Association for Computational Linguistics 2023
• Proceedings of the AAAI Conference on Artificial Intelligence ×3
• Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) ×2
• ACM Computing Surveys: ACM Computing Surveys 2023
• Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026
• Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
• Findings of the Association for Computational Linguistics: EMNLP 2023
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
• IEEE/CVF International Conference on Computer Vision (ICCV)
• International Joint Conference on Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 1,471 times (of the 149,439 papers whose bibliographies we read); 254 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/fei-qing-wu/