---

My Research

My research focuses on natural language processing and multimodal artificial intelligence, with particular interests in large language models, multimodal understanding, information extraction, spoken language understanding, and sentiment analysis. I aim to develop robust, generalizable, and explainable intelligent systems by exploring advanced learning and reasoning techniques.

---

Publications

(# denotes equal contribution, * denotes corresponding author)

2026

• Bridging Generation and Parsing: Collaborative Self-Distillation for Zero-shot Multi-Intent Spoken Language Understanding. .
  Aziguli Wulamu, Ao He, Dezheng Zhang, Jun Li, Xinyuan Qian, Zhihong Zhu, Libo Qin and Bowen Xing^*
  In In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026).

• Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework.
  Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu and Min Zhang
  In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) .

• Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization.
  Zixuan Huang, Zhihong Zhu, Xiaolong Liu, Yanchao Hao, Manman Zhang, Zheng Wei, Bowen Xing, Xian Wu, Ye Li, Fen Miao and Yefeng Zheng
  In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) .

• Bridging Reasoning and Action: Hybrid LLM–RL Framework for Efficient Cross-Domain Task-Oriented Dialogue.
  Yangyang Zhao, Linfan Dai, Li Cai, Bowen Xing and Libo Qin
  In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)[Findings] .

• S³-MSD: Large Vision-Language Model for Explainable and Generalizable Multi-modal Sarcasm Detection.
  Zhihong Zhu, Fan Zhang, Yunyan Zhang, Jinghan Sun, Guimin Hu, Hao Wu, Yuyan Chen, Bowen Xing and Xian Wu
  In the Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026).

• CMID: Towards Medical Visual Question Answering via Contrastive Mutual Information Decoding.
  Zhihong Zhu, Yunyan Zhang, Fan Zhang, Bowen Xing and Xian Wu
  In the Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026).

2025

• RTE-GMoE: A Model-agnostic Approach for Relation Triplet Extraction via Graph-based Mixture-of-Expert Mutual Learning.
  Aziguli Wulamu, Kaiyuan Gong, Lyu Zhengyu, Yu Han, Zhihong Zhu and Bowen Xing^*
  In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) .

• A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers.
  Zhihong Zhu, Fan Zhang, Yunyan Zhang, Yunyan_Zhang, Jinghan Sun, Zhiqi Huang, QingqingLong, Bowen Xing and Xian Wu.
  In Findings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025 Findings) .

• HTML: Hierarchical Topology Multi-task Learning for Semantic Parsing in Knowledge Base Question Answering.
  Aziguli Wulamu, Lyu Zhengyu, Kaiyuan Gong, Yu Han, Zewen Wang, Zhihong Zhu and Bowen Xing^*.
  In Proceedings of the 63th Annual Meeting of the Association for Computational Linguistics (ACL 2025) [Findings].

• Sentence-level Relation Semantics Learning via Contrastive Sentences .
  Bowen Xing^* and Ivor W. Tsang.
  In IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2025 .

• DXA-Net: Dual-task Cross-lingual Alignment Network for Zero-shot Cross-lingual Spoken Language Understanding.
  Bowen Xing, Libo Qin, Zhou Yu and Ivor W. Tsang.
  In IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2025.

• DigNet: Digging Clues from Local-Global Interactive Graph for Aspect-level Sentiment Classification.
  Bowen Xing^* and Ivor W. Tsang.
  In IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2025.

2024

• DC-Instruct: An Effective Framework for Generative Multi-intent Spoken Language Understanding.
  Bowen Xing^*, Lizi Liao, Minlie Huang and Ivor W. Tsang.
  In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024) .

• InMu-Net: Advancing Multi-modal Intent Detection via Information Bottleneck and Multi-sensory Processing.
  Zhihong Zhu, Xuxin Cheng, Zhaorun Chen, Yuyan Chen, Yunyan Zhang, Xian Wu, Yefeng Zheng and Bowen Xing.
  In ACM Multimedia 2024 .

• Low-Hanging Fruit: Knowledge Distillation from Noisy Teachers for Open Domain Spoken Language Understanding.
  Cheng Chen, Bowen Xing and Ivor W. Tsang.
  In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2024) .

• HC²L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding .
  Bowen Xing^* and Ivor W. Tsang.
  In IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024 .

• Exploiting Contextual Target Attributes for Target Sentiment Classification.
  Bowen Xing^* and Ivor W. Tsang.
  In Journal of Artificial Intelligence Research (JAIR), 2024 .

2023

• MTKDN: Multi-Task Knowledge Disentanglement Network for Recommendation.
  Haotian Wu^#, Bowen Xing^#* and Ivor W. Tsang.
  In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023) [short paper].

• Co-evolving Graph Reasoning Network for Emotion-Cause Pair Extraction.
  Bowen Xing^* and Ivor W. Tsang.
  In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2023) [Oral] .

• Co-guiding for Multi-intent Spoken Language Understanding .
  Bowen Xing^* and Ivor W. Tsang.
  In IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2023 .

• Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding
  Bowen Xing^* and Ivor W. Tsang.
  In IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2023 .

2022

• Co-guiding Net: Modeling Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogenous Semantics-Label Graphs.
  Bowen Xing^* and Ivor W. Tsang.
  In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) [Oral].

• Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling.
  Bowen Xing^* and Ivor W. Tsang.
  In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022) .

• Neural Subgraph Explorer: Reducing Noisy Information via Target-oriented Syntax Graph Pruning.
  Bowen Xing^* and Ivor W. Tsang.
  In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI 2022) [Oral].

• DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition.
  Bowen Xing^* and Ivor W. Tsang.
  In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022) [Findings].

• Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis.
  Bowen Xing^* and Ivor W. Tsang.
  In Journal of Artificial Intelligence Research (JAIR), 2022 .

• Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network.
  Bowen Xing^* and Ivor W. Tsang.
  In IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI), 2022 .

2019

• Earlier Attention? Aspect-Aware LSTM for Aspect-Based Sentiment Analysis.
  Bowen Xing, Lejian Liao, Dandan Song, Jingang Wang, Fuzheng Zhang, Zhongyuan Wang and Heyan Huang.
  In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019) [Oral].

---

Professional Service

• Conference Reviewer/PC Member/Area Chair:

• ACL, ICML, NeurIPS, EMNLP, AAAI, etc.

• Journal Reviewer:

• TPAMI, TNNLS, TASLP, KAIS, etc.