Ethan, Wenjun Hou (侯文俊) 🏖 PhD Student1,2 1 Department of Computing, The Hong Kong Polytechnic University (PolyU) 2 Department of Computer Science and Engineering, Southern University of Science and Technology (SUSTech) Email: houwenjun060 (at) gmail.com   or                wenjun.hou (at) connect.polyu.hk [Resume] [Github] [Google Scholar] [Twitter]

I am currently on the job market and actively looking for industry opportunities. 🚀🚀🚀

I am a final-year joint Ph.D. student, advised by Prof. Maggie, Wenjie Li@NLP Group, PolyU and Prof. Jiang Liu@iMED Shenzhen, SUSTech. I received my Master's degree from China Agricultural University (CAU) in 2020, and Bachelor's degree from Guangdong University of Technology (GDUT) in 2017.

News

[Sep. 2024] 🔥 ICon is accepted by EMNLP 2024 Findings.

Research

Currently, I am working on Natural Language Processing and Multimodal Learning. Especially, I focus on the following directions:

• Medical Report Generation: Accurate (ORGan@ACL'23) , Precise (Recap@EMNLP'23 Findings) , and Consistent (ICon@EMNLP'24 Findings) Radiology Report Generation;
• Medical VQA: Memory-Augmented MLLMs for Surgical VQA (S²Can@arXiv).
• Healthcare Agents: interested in developing healthcare agents that can utilize other medical applications (e.g., medical report generation systems) and provide consultations (DFMed@ACL'23 Findings, Emulation@ACL'24 Findings and IADDx@arXiv).

Always open to collaboration. Feel free to drop an email and I'll be happy to have a discussion. 😁

Publications

(*: equal contribution)

Preprint

• Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry
  Wenjun Hou, Kaishuai Xu, Yi Cheng, Yan Hu, Wenjie Li, Jiang Liu
  arXiv, 2024.
  [arXiv]
• Subtle Errors Matter: Preference Learning via Error-injected Self-editing
  Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li
  arXiv, 2024.
  [arXiv]
• Integrative Decoding: Improve Factuality via Implicit Self-consistency
  Yi Cheng, Xiao Liang, Yeyun Gong, Wen Xiao, Song Wang, Yuji Zhang, Wenjun Hou, Kaishuai Xu, Wenge Liu, Wenjie Li, Jian Jiao, Qi Chen, Peng Cheng, Wayne Xiong
  arXiv, 2024.
  [arXiv][code]
• AutoPal: Autonomous Adaptation to Users for Personal AI Companisonship
  Yi Cheng, Wenge Liu, Kaishuai Xu, Wenjun Hou, Yi Ouyang, Chak Tou Leong, Xian Wu, Yefeng Zheng.
  arXiv, 2024.
  [arXiv]
• Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis
  Kaishuai Xu, Wenjun Hou*, Yi Cheng*, Jian Wang, Wenjie Li.
  arXiv, 2024.
  [arXiv]
  

2021 - Present

• ICon: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation
  Wenjun Hou, Yi Cheng*, Kaishuai Xu*, Yan Hu, Wenjie Li, Jiang Liu.
  Findings of the Association for Computational Linguistics: EMNLP 2024 (EMNLP Findings), 2024.
  [project][paper][arXiv][code]
  
• Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process Alignment
  Kaishuai Xu, Yi Cheng*, Wenjun Hou*, Qiaoyu Tan, Wenjie Li.
  Findings of the Association for Computational Linguistics: ACL 2024 (ACL Findings), 2024.
  [paper][arXiv][code]
• Recap: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning
  Wenjun Hou, Yi Cheng*, Kaishuai Xu*, Wenjie Li, Jiang Liu.
  Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP Findings), 2023.
  [project][paper][arXiv][code][poster]
  
• ORGan: Observation-Guided Radiology Report Generation via Tree Reasoning
  Wenjun Hou, Kaishuai Xu*, Yi Cheng*, Wenjie Li, Jiang Liu.
  Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023.
  [project][paper][arXiv][code][video]
  
• Medical Dialogue Generation via Dual Flow Modeling
  Kaishuai Xu, Wenjun Hou*, Yi Cheng*, Jian Wang, Wenjie Li.
  Findings of the Association for Computational Linguistics: ACL 2023 (ACL Findings), 2023.
  [paper][arXiv][code]
  

2018 - 2020 (Before PhD)

• End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network
  Ying Chen, Wenjun Hou, Shoushan Li, Caicong Wu, Xiaoqiang Zhang.
  Proceedings of the 28th International Conference on Computational Linguistics (COLING), 2020.
  [paper][code]
  
• Sentence-Level Propaganda Detection Using BERT with Context-Dependent Input Pairs
  Wenjun Hou, Ying Chen.
  Proceedings of the 2nd Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda (NLP4IF), 2019.
  [paper][code]
• Joint Learning for Emotion Classification and Emotion Cause Detection
  Ying Chen, Wenjun Hou, Xiyao Cheng, Shoushan Li.
  Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
  [paper]

Experience

• Research Intern, DiDi Global, 12/2018 - 03/2019.

Professional Activities

Teaching Assistant

• TA for COMP4424 Extended Reality: Theory and Practice, Spring 2023, PolyU.
• TA for COMP2S01 Technology Beyond Borders: Service Learning Across Cultural, Ethnic and Community Lines, Fall 2022 / Spring 2022 / Fall 2021, PolyU.
• TA for Computational Methods, Fall 2019, CAU.

Conference Reviewer

• ICLR (2025), ACL ARR (2024 Feb, Apr), EMNLP (2023, 2022), COLING (2025, 2024, 2022)