🧑‍🔬 Junnan Zhu

🏛️ Affiliations

🔬Institute of AutomationBeijing · China2017–2026 · 57 paperscurrent🏛️Chinese Academy of SciencesBeijing · China2018–2026 · 56 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2017–2026 · 27 paperscurrent🏢Shenyang Institute of Computing TechnologyShenyang · China2026 · 2 paperscurrent🔬National Supercomputing Center in JinanJinan · China2026 · 1 papercurrent🎓Qilu University of TechnologyJinan · China2026 · 1 papercurrent🎓Shandong Academy of SciencesJinan · China2026 · 1 papercurrent

🏛️Institute of Automation Chinese Academy of SciencesBeijing · China2015–2023Education 2015–2020 · Doctor, National Laboratory of Pattern RecognitionEmployment 2020–2023 · Assistant ProfessorEmployment since 2023 · Associate ProfessorEmployment since 2023

🎓Central South UniversityChangsha · China2011–2015Education 2011–2015 · Bachelor, School of Information Science and Engineering

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution 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. MSMO: Multimodal Summarization with Multimodal Output (2018 · 245 citations)
   The paper argues that summaries of multimedia news should be multimodal themselves. It introduces MSMO, a task where a system receives an article plus an unaligned set of images and must return a short text summary together with the single most relevant image. The authors built a large corpus from the Daily Mail…
2. TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering (2025 · 7 citations)
   TableEval addresses weaknesses in existing table question answering (TableQA) benchmarks. Most rely on simple flat tables, cover a single language, and may overlap with LLM pretraining data. The authors gathered tables from documents published in 2024, drawn from government, finance, academic and industry-report…
3. TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification (2025 · 6 citations)
   TROVE frames text provenance as a fine-grained task. For every sentence of a generated or target text, a system must find the exact source sentences it came from, even when the input is long or split across several documents. It must also label how each sentence was derived: quotation, compression, inference, or…
4. From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation (2026)
   Generative recommenders produce semantic item IDs one step at a time. This left-to-right training tends to anchor them on the most recent interactions and miss longer-range user intent. To counter this, the authors introduce Masked History Learning (MHL), which changes how decoder-only generative models are trained.…
5. GenProve: Learning to Generate Text with Fine-Grained Provenance (2026)
   Citations in LLM answers often point only to whole documents. They do not show which sentence backs a claim or how that sentence is used, so checking the answer stays hard. The authors define a task called Generation-time Fine-grained Provenance. The model writes an answer and, for each sentence, emits structured…
6. MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis (2026)
   The paper tackles automated psychiatric diagnosis with LLMs. Existing evaluation data are mostly social-media posts or synthetic stories with coarse labels, so they say little about real clinical use. The authors build MentalDx Bench from 712 de-identified electronic health records collected at partner hospitals.…

All works

11 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. MSMO: Multimodal Summarization with Multimodal OutputConference on Empirical Methods in Natural Language Processing (EMNLP)Junnan Zhu, Haoran Li, Tianshang Liu, et al.2018 · 245 citations
2. NCLS: Neural Cross-Lingual Summarization ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetJunnan Zhu et al.2019 · 174 citations
3. Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video ↗Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · no summary yetHaoran Li et al.2017 · 141 citations
4. Multimodal Summarization with Guidance of Multimodal Reference ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetJunnan Zhu et al.2020 · 129 citations
5. Keywords-Guided Abstractive Sentence Summarization ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetHaoran Li et al.2020 · 107 citations
6. Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetJunnan Zhu et al.2020 · 69 citations
7. TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP)Junnan Zhu, Jingyi Wang, Bohan Yu, et al.2025 · 7 citations
8. TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL)Junnan Zhu, Min Xiao, Yining Wang, et al.2025 · 6 citations
9. From Past To Path: Masked History Learning for Next-Item Prediction in Generative RecommendationAnnual Meeting of the Association for Computational Linguistics (ACL)Kaiwen Wei, Kejun he, Xiaomian Kang, et al.2026
10. GenProve: Learning to Generate Text with Fine-Grained ProvenanceAnnual Meeting of the Association for Computational Linguistics (ACL)Jingxuan Wei, Xingyue Wang, Yanghaoyu Liao, et al.2026
11. MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric DiagnosisAnnual Meeting of the Association for Computational Linguistics (ACL)Xiao Sun, Ymyang, Xinyi Jiang, et al.2026

🤝 Co-authors here

12 of 21 co-authors with a page, the most papers together first.

• Chengqing Zong ×2
• Jiang Zhong ×2
• Kaiwen Wei ×2
• Ymyang ×2
• Yu Zhou ×2
• Bihui Yu
• Bohan Yu
• Feifei Zhai
• Haoran Li
• Jiajun Zhang
• Jie Zhang
• Jingxuan Wei

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) ×5: ACL 2026 ×3, ACL 2025
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×3: EMNLP 2025, EMNLP 2018
• Proceedings of the AAAI Conference on Artificial Intelligence ×2
• Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

🔗 Cited by

Papers of our library cite their works 244 times (of the 149,439 papers whose bibliographies we read); 9 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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