PhD student at NUS
NExT++ Research Center
NUS Institute of Data Science
NUS School of Computing
Email: acharkq at gmail.com
• Google Scholar Page • GitHub Page • Twitter/X
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
ReactXT: Understanding Molecular “Reaction-ship” via Reaction-Contextualized Molecule-Text Pretraining.
ProtT3: Protein-to-Text Generation for Text-based Protein Understanding.
MolTC: Towards Molecular Relational Modeling In Language Models.
Towards 3D Molecule-Text Interpretation in Language Models.
MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter.
ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction.
Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules.
Selected Publications (Google Scholar)
ACL'24
|
ProtT3: Protein-to-Text Generation for Text-based Protein Understanding. [Paper; Code] Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua. |
ACL Findings'24
|
ReactXT: Understanding Molecular “Reaction-ship” via Reaction-Contextualized Molecule-Text Pretraining. [Paper; Code; Demo; Website] Zhiyuan Liu*, Yaorui Shi*, An Zhang, Sihang Li, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua. |
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. |
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 |
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. |
* denotes equal contribution. |
Academic Service
I am serving as an Action Editor (Area Chair) for ACL2024 (ARR Feburary 2024), EMNLP 2024 (ARR June 2024), and NAACL2024 (ARR December 2023). I have also served as a Reviewer for ICLR2024, NeurIPS 2024, NeurIPS2023, NeurIPS2022, NeurIPS2021, ICML2024, ICML2023, ICML2022, COLM 2024 etc. I am also reviewing top journals like TPAMI and TKDE.
Teaching Assistant
Honors and Awards
Background
Supervisor: Prof. Chua Tat-Seng; Co-supervisor: Prof. Kawaguchi Kenji; Mentor: Prof. Wang Xiang