π― About Me
I am Fangzhi Xu (εΎζΉζ€), a second-year PhD student in Xiβan Jiaotong University, major in Computer Science, advised by Prof. Jun Liu. I am currently a research intern at Shanghai AI LAB, supervised by Dr. Zhiyong Wu.
I have published researches in some top-tier conferences and journals, such as ACL, SIGIR, and IEEE TKDE. Also, I serve as a PC member (or reviewer) for ACL, NAACL, IJCAI, SIGIR.
Research Interests
In general, my research interests lie in natural language processing, large language models and neuro-symbolic reasoning.
Currently, my researches cover the following topics:
- LLM + Neuro-Symbolic: ENVISIONS(Preprint), Symbol-LLM(ACLβ24)
- Logical Reasoning: PathReasoner(ACLβ24), Logiformer(SIGIRβ22), TaCo(IEEE TNNLS), Evaluation Paper(IEEE TKDE under review)
- (Multimodal) Autonomous Agents: SeeClick(ACLβ24), OS-Atlas(Preprint)
π₯ News
- 2024.10.31: Β Our papers [OS-Atlas, AgentStore, R3-V] are recently released ππ!
- 2024.05.20: Β Our paper ENVISIONS is recently released ππ!
- 2024.05.16: Β Three papers are accepted by ACL 2024 (main conference) ππ!
- 2024.03.24: Β Our recent survey on neural code intelligence is made public ππ!
- 2024.02.20: Β One paper is accepted by COLING 2024 ππ!
- 2024.02.10: Β One paper is accepted by ICDE 2024 (TKDE Poster Track) ππ!
- 2023.11.15: Β We make the recent work Symbol-LLM public π!
π Educations
- 2021.09 - 2026.06 (expected), M.S. + Ph.D Student, Computer Science, Xiβan Jiaotong University. β
- 2017.09 - 2021.06, B.S. in Electrical Engineering, Xiβan Jiaotong University. β GPA:97.62/100, Rankings:1/365
π» Internships
- 2023.07 - Present, Research Intern @ Shanghai AI LAB. Focus on Large Language Models and Neuro-Symbolic.
π Selected Publications
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents π₯π₯ [Preprint]
Zhiyong Wu*, Zhenyu Wu*, Fangzhi Xu*, Yian Wang*, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, Yu Qiao
(* means equal contributions)
Code Β Project Page Β Demo Β
Interative Evolution: A Neural-symbolic Self-Training Framework for Large Language Models π₯π₯ [Preprint]
Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, Jun Liu, Yu Qiao, Zhiyong Wu.
Code Β Project Page Β Β
Symbol-LLM: Towards Foundational Symbol-centric Interface
For Large Language Models [CCF-A]
Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Qiao Yu and Jun Liu.
Code Β Project Page Β Β
PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering [CCF-A]
Fangzhi Xu, Qika Lin, Tianzhe Zhao, Jiawei Han, Jun Liu
Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond Under Review at IEEE TKDE [CCF-A]
Fangzhi Xu*, Qika Lin*, Jiawei Han, Tianzhe Zhao, Jun Liu and Erik Cambria
(* means equal contributions)
Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning [CCF-A]
Fangzhi Xu, Jun Liu, Qika Lin, Yudai Pan and Lingling Zhang
π§β Other Paper
Preprint
Vision-Language Models Can Self-Improve Reasoning via Reflection
Kanzhi Cheng, Yantao Li, Fangzhi Xu, Jianbing Zhang, Hao Zhou, Yang LiuPreprint
AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant
Chengyou Jia, Minnan Luo, Zhuohang Dang, Qiushi Sun, Fangzhi Xu, Junlin Hu, Tianbao Xie, Zhiyong WuPreprint
A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond
Qiushi Sun, Zhirui Chen, Fangzhi Xu, Chang Ma, Kanzhi Cheng, Zhangyue Yin, Jianing Wang, Chengcheng Han, Renyu Zhu, Shuai Yuan, Pengcheng Yin, Qipeng Guo, Xipeng Qiu, Xiaoli Li, Fei Yuan, Lingpeng Kong, Xiang Li, Zhiyong WuACL 2024
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents [CCF-A]
Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, Zhiyong WuCOLING 2024
A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction [CCF-B]
Jian Zhang, Changlin Yang, Haiping Zhu, Qika Lin, Fangzhi Xu and Jun LiuACL 2023
TECHS: Temporal Logical Graph Networks for Explainable Extrapolation Reasoning [CCF-A]
Qika Lin, Jun Liu, Rui Mao, Fangzhi Xu and Erik CambriaInformation Fusion
Fusing Topology Contexts and Logical Rules in Language Models for Knowledge Graph Completion [SCI-Q1]
Qika Lin, Rui Mao, Jun Liu, Fangzhi Xu, Erik CambriaIEEE TNNLS
Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text [CCF-B]
Fangzhi Xu, Jun Liu, Qika Lin, Tianzhe Zhao, Jian Zhang, Lingling ZhangAPWEB-WAIM 2022
Incorporating Prior Type Information for Few-shot Knowledge Graph Completion [CCF-C] (Excellent Student Paper)
Siyu Yao, Tianzhe Zhao, Fangzhi Xu, Jun LiuSIGIR 2022
Incorporating Context Graph with Logical Reasoning for Inductive Relation Prediction [CCF-A]
Qika Lin, Jun Liu, Fangzhi Xu, Yudai Pan, Yifan Zhu, Lingling Zhang and Tianzhe ZhaoPattern Recognition
MoCA: Incorporating Domain Pretraining and Cross Attention for Textbook Question Answering [CCF-B]
Fangzhi Xu, Qika Lin, Jun Liu, Lingling Zhang, Tianzhe Zhao, Qi Chai, Yudai PanIEEE TKDE
Contrastive Graph Representations for Logical Formulas Embedding [CCF-A]
Qika Lin, Jun Liu, Lingling Zhang, Yudai Pan, Xin Hu, Fangzhi Xu, Hongwei Zeng
π Honors and Awards
Honors
- Oct.2022 β Outstanding Student in Xiβan Jiaotong University
- Jun.2021 β Outstanding Undergraduate Graduates in Shaanxi Province
- Sep.2020 β Top-10 Students of the Year (Top Personal Award in Xiβan Jiaotong University)
- Sep.2019 β Outstanding Student in Xiβan Jiaotong University
- Sep.2018 β Outstanding Student in Xiβan Jiaotong University
Competition Awards
- Dec.2022 β βHuawei Cupβ Mathematical Contest in Modeling, Second Prize
- Mar.2022 β Asia and Pacific Mathematical Contest in Modeling (APMCM), First Prize + Innovation Award (Top-2)
- Dec.2021 β βHuawei Cupβ Mathematical Contest in Modeling, Second Prize
- Sep.2020 β IKCEST International Big Data Competition, Excellence Award
- Apr.2020 β Mathematical Contest in Modeling (COMAP), Finalist
- Dec.2019 β China Mathematical Contest in Modeling (CUMCM), Second Prize
- May.2018 β National English Competition for College Students (NECCS), Second Prize
π Scholarships
- 2023.09 β Freshman First Prize Scholarship (PhD)
- 2022.09 β National Scholarship
- 2022.09 β Huawei Scholarship
- 2022.04 β ACM SIGIR Student Travel Grant
- 2021.09 β Freshman First Prize Scholarship (Master)
- 2020.09 β Chinese Modern Scientists Scholarship (Only for Top-10 Student)
- 2019.09 β National Scholarship
- 2018.09 β National Scholarship
π¬ Academic Services
- Program Committee Member: ACL ARR 2024, IJCAI 2024, SIGIR 2024, AACL 2023, SIGIR 2023, SIGIR-AP 2023
- Reviewer: IEEE TNNLS