Zhaowei Wang

Research Highlights by Topic

MLLMs and Their Agent Usage

1. arXiv

   MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

   Zhaowei Wang, Wenhao Yu, Xiyu Ren, Jipeng Zhang, Yu Zhao, Rohit Saxena, Liang Cheng, Ginny Wong, Simon See, Pasquale Minervini, Yangqiu Song, and Mark Steedman

   arXiv Code Website
2. arXiv

   Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions

   Yiming Du, Wenyu Huang, Danna Zheng, Zhaowei Wang, Sebastien Montella, Mirella Lapata, Kam-Fai Wong, and Jeff Z. Pan

   arXiv Code
3. arXiv

   DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects

   Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, and Dong Yu

   arXiv Code Website

Abstraction Knowledge

1. NAACL

   Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction

   Kaiqiao Han, Tianqing Fang, Zhaowei Wang, Yangqiu Song, and Mark Steedman

   In 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

   arXiv Code
2. ACL

   AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

   Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Y. Wong, and Simon See

   In The 62nd (2024) Annual Meeting of the Association for Computational Linguistics

   arXiv Code
3. NAACL

   AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph

   Zhaowei Wang, Haochen Shi, Weiqi Wang, Tianqing Fang, Hongming Zhang, Sehyun Choi, Xin Liu, and Yangqiu Song

   In Findings of 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

   arXiv Code

Discourse Relations:

1. EMNLP

   SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller

   Zhaowei Wang, Hongming Zhang, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, and Simon See

   In 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) (*oral)

   arXiv Code