Publications

reversed chronological order.

This page may not always be fully up to date. For the most current and complete list of publications, please see my Google Scholar profile.

arXiv

  1. arXiv
    MEMLENS: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
    Xiyu Ren, Zhaowei Wang, Yiming Du, Zhongwei Xie, Chi Liu, Xinlin Yang, Haoyue Feng, Wenjun Pan, Tianshi Zheng, Baixuan Xu, and  others
    arXiv
  2. arXiv
    Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models (MMRetHeads)
    Aaron Branson Cigres Li*, Zhaowei Wang*, Yu Zhao, Yiming Du, Haobo Li, Xiyu Ren, Ginny Wong, Simon See, Lishu Luo, Haodong Duan, and  others
    arXiv
  3. arXiv
    Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context (MMProLong)
    Zhaowei Wang, Lishu Luo, Haodong Duan, Weiwei Liu, Sijin Wu, Ji Luo, Shen Yan, Shuai Peng, Sihang Yuan, Chaoyi Huang, and  others
    arXiv
  4. arXiv
    VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
    Jipeng Zhang, Kehao Miao, Renjie Pi, Zhaowei Wang, Runtao Liu, Rui Pan, and Tong Zhang
    arXiv
  5. 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

2025

  1. Report
    Seed1.8 model card: Towards generalized real-world agency
    ByteDance Seed Team
    arXiv
  2. ICLR
    Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
    Yiming Du, Baojun Wang, Yifan Xiang, Zhaowei Wang, Wenyu Huang, Boyang Xue, Bin Liang, Xingshan Zeng, Fei Mi, Haoli Bai, and  others
    arXiv
  3. NeurIPS
    MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly (*spotlight)
    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
    In The 39th (2025) Annual Conference on Neural Information Processing Systems
    arXiv Code Website
  4. NeurIPS
    PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series
    Haobo Li, Eunseo Jung, Zixin Chen, Zhaowei Wang, Yueya Wang, Huamin Qu, and Alexis Kai Hon Lau
    In The 39th (2025) Annual Conference on Neural Information Processing Systems
    arXiv
  5. NeurIPS LAW
    Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
    Xingyue Huang,  Rishabh, Gregor Franke, Ziyi Yang, Jiamu Bai, Weijie Bai, Jinhe Bi, Zifeng Ding, Yiqun Duan, Chengyu Fan, Wendong Fan, Xin Gao, Ruohao Guo, Yuan He, Zhuangzhuang He, Xianglong Hu, Neil Johnson, Bowen Li, Fangru Lin, Siyu Lin, Tong Liu, Yunpu Ma, Hao Shen, Hao Sun, Beibei Wang, Fangyijie Wang, Hao Wang, Haoran Wang, Yang Wang, Yifeng Wang, Zhaowei Wang, Ziyang Wang, Yifan Wu, Zikai Xiao, Chengxing Xie, Fan Yang, Junxiao Yang, Qianshuo Ye, Ziyu Ye, Guangtao Zeng, Yuwen Ebony Zhang, Zeyu Zhang, Zihao Zhu, Bernard Ghanem, Philip Torr, and Guohao Li
    In NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning (LAW Workshop@NeurIPS 2025)
    arXiv Code
  6. EMNLP
    S2LPP: Small-to-Large Prompt Prediction across LLMs
    Liang Cheng, Tianyi LI, Zhaowei Wang, and Mark Steedman
    In The 2025 Conference on Empirical Methods in Natural Language Processing
    arXiv
  7. EMNLP
    DivScene: Evaluating Large Vision Language Models for Object Navigation with Open-Vocabulary Targets in Diverse Scenes
    Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, and Dong Yu
    In The 2025 Conference on Empirical Methods in Natural Language Processing
    arXiv Code Website
  8. EMNLP
    CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting
    Haobo Li, Zhaowei Wang, Jiachen Wang, Alexis Kai Hon Lau, and Huamin Qu
    In The 2025 Conference on Empirical Methods in Natural Language Processing
    arXiv
  9. LCFM@ICML
    MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly (Workshop Version)
    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
    In Workshop on long-context foundation models (LCFM) @ ICML 2025
    PDF Code Website
  10. ACL
    Neutralizing Bias in LLM Reasoning using Entailment Graphs
    Liang Cheng, Tianyi Li, Zhaowei Wang, Tianyang Liu, and Mark Steedman
    In The 63nd (2025) Annual Meeting of the Association for Computational Linguistics
    arXiv
  11. ACL
    ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty
    Qing Zong, Zhaowei Wang, Tianshi Zheng, Xiyu Ren, and Yangqiu Song
    In The 63nd (2025) Annual Meeting of the Association for Computational Linguistics
    arXiv
  12. ICMLC
    Balanced KGQA through Prompt-Based Data Augmentation with LLMs
    Xiyu Ren, and Zhaowei Wang
    In 2025 17th International Conference on Machine Learning and Computing
  13. 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

2024

  1. arXiv
    What Really is Commonsense Knowledge?
    Quyet V. Do, Junze Li, Tung-Duong Vuong, Zhaowei Wang, Yangqiu Song, and Xiaojuan Ma
    arXiv
  2. arXiv
    CodeGraph: Enhancing Graph Reasoning of LLMs with Code
    Qiaolong Cai*, Zhaowei Wang*, Shizhe Diao, James Kwok, and Yangqiu Song
    In arXiv
    arXiv Code
  3. EMNLP
    LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
    Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Peng Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Ranran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Jiayang Cheng, Zhaowei Wang, Ying Su, Raj Sanjay Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip S. Yu, and Wenpeng Yin
    In 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)
    arXiv
  4. ArgMining
    KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining
    Zihao Zheng, Zhaowei Wang, Qing Zong, and Yangqiu Song
    In Proceedings of the 11th Workshop on Argument Mining (at ACL 2024)
    arXiv Code
  5. 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
  6. ACL
    CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning
    Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Jiayang Cheng, Chunkit Chan, and Yangqiu Song
    In The 62nd (2024) Annual Meeting of the Association for Computational Linguistics
    arXiv Code
  7. 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
  8. NAACL
    Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
    Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, and Muhao Chen
    In Findings of 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
    arXiv
  9. EACL
    ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases
    Quyet V. Do, Tianqing Fang, Shizhe Diao, Zhaowei Wang, and Yangqiu Song
    In 2024 Conference of the European Chapter of the Association for Computational Linguistics (EACL)
    arXiv Code

2023

  1. EMNLP
    KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection
    Sehyun Choi, Tianqing Fang, Zhaowei Wang, and Yangqiu Song
    In 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)
    arXiv Code
  2. EMNLP
    Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection
    Zheye Deng, Weiqi Wang, Zhaowei Wang, Xin Liu, and Yangqiu Song
    In Findings of 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)
    arXiv Code
  3. ArgMining
    TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining
    Qing Zong, Zhaowei Wang, Baixuan Xu, Tianshi Zheng, Haochen Shi, Weiqi Wang, Yangqiu Song, Ginny Wong, and Simon See
    In Proceedings of the 10th Workshop on Argument Mining (at EMNLP 2023)
    arXiv Code
  4. WMT
    KnowComp Submission for WMT23 Sign Language Translation Task
    Baixuan Xu, Haochen Shi, Tianshi Zheng, Qing Zong, Weiqi Wang, Zhaowei Wang, and Yangqiu Song
    In Proceedings of the Eighth Conference on Machine Translation (WMT at EMNLP 2023)
  5. ACL
    COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective (*oral)
    Zhaowei Wang, Quyet V. Do, Hongming Zhang, Jiayao Zhang, Weiqi Wang, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, and Simon See
    In 2023 Annual Meeting of the Association for Computational Linguistics (ACL)
    arXiv Code

2022

  1. EMNLP
    SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller (*oral)
    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)
    arXiv Code
  2. IJCNN
    Legal Element-oriented Modeling with Multi-view Contrastive Learning for Legal Case Retrieval
    Zhaowei Wang
    In 2022 International Joint Conference on Neural Networks (IJCNN)
    arXiv PDF

2020

  1. JSS
    Bug severity prediction using question-and-answer pairs from Stack Overflow
    Youshuai Tan, Sijie Xu, Zhaowei Wang, Tao Zhang, Zhou Xu, and Xiapu Luo
    Journal of Systems and Software
    PDF
  2. ICCCN
    Practical and White-Box Anomaly Detection through Unsupervised and Active Learning
    Yao Wang, Zhaowei Wang, Zejun Xie, Nengwen Zhao, Junjie Chen, Wenchi Zhang, Kaixin Sui, and Dan Pei
    In 2020 29th International Conference on Computer Communications and Networks (ICCCN)
    PDF