Biography

I am a PhD student at NExT++, where I am supervised by Prof. Chua Tat-Seng and co-supervised by Prof. Kawaguchi Kenji. I am also fortunate to be mentored by Prof. Wang Xiang at the University of Science and Technology of China (USTC). My research primarily focuses on AI for Science, particularly Multi-modal Generative Modeling for emerging scientific modalities such as molecules and proteins. Additionally, I have a keen interest in Graph Neural Networks and Natural Language Processing.

News

[New!] 2024/01 One paper is accepted by ICLR 2024!
     Towards 3D Molecule-Text Interpretation in Language Models.

[New!] 2023/10 Two papers are accepted by EMNLP 2023, one for the EMNLP main conference and one for the EMNLP Findings!
     MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter.
     ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction.

[New!] 2023/09 One paper is accepted by NeurIPS'23!
     Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules.

Publications

ICLR'24	Towards 3D Molecule-Text Interpretation in Language Models. [Paper; Code] Sihang Li*, Zhiyuan Liu*, Yanchen Luo, Xiang Wang, Xiangnan He, Kenji Kawaguchi, Tat-Seng Chua, Qi Tian.
EMNLP'23	MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter. [Paper; Code; Website] Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, and Tat-Seng Chua.
EMNLP Findings'23	ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction. [Paper; Code] Yaorui Shi, An Zhang, Enzhi Zhang, Zhiyuan Liu, and Xiang Wang
NeurIPS'23	Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules. [Paper; Code] Zhiyuan Liu, Yaorui Shi, An Zhang, Enzhi Zhang, Kenji Kawaguchi, Xiang Wang, and Tat-Seng Chua
AAA'21	Video as Conditional Graph Hierarchy for Multi-Granular Question Answering. [Paper; Code] Junbin Xiao, Angela Yao, Zhiyuan Liu, Yicong Li, Wei Ji, and Tat-Seng Chua
EMNLP'20	Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment. [Paper; Code] Zhiyuan Liu, Yixin Cao, Liangming Pan, Juanzi Li, Zhiyuan Liu, and Tat-Seng Chua.
ACL'19	Multi-Channel Graph Neural Network for Entity Alignment. [Paper; Code] Yixin Cao, Zhiyuan Liu, Chengjiang Li, Zhiyuan Liu, Juanzi Li, and Tat-Seng Chua.
CCL'19	Legal Cause Prediction with Inner Descriptions and Outer Hierarchies [Paper; Code] Zhiyuan Liu, Cunchao Tu, Zhiyuan Liu, and Maosong Sun
* denotes equal contribution.

Honors and Awards

Dean's Graduate Research Excellence Award, National University of Singapore 2023

Student Research Award, Institue of Data Science at NUS 2023

Research Achievement Award, National University of Singapore 2021

National Group First Prize, the 7th China Undergraduate Physics Tournament 2016

Academic Service

I am serving as an Action Editor (Area Chair) for ACL2024 (ARR Feburary 2024) and NAACL2024 (ARR December 2023). I have also served as a Reviewer for ICLR2024, NeurIPS2023, NeurIPS2022, NeurIPS2021, ICML2024, ICML2023, ICML2022, etc.

Background

PhD student in Computer Science, NExT++, National University of Singapore, 2020-Present
     Supervisor: Prof. Chua Tat-Seng; Co-supervisor: Prof. Kawaguchi Kenji; Mentor: Prof. Wang Xiang

Bachelor in Physics, Xi'an Jiaotong University, 2015-2019