Liang Wang (王亮)
Hi! I am Liang Wang, a final-year PhD student at Institute of Automation, Chinese Academy of Sciences (CASIA), where I am affiliated with the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), supervised by Prof. Liang Wang (in a curious coincidence, my supervisor's name is spelled identically to mine) and co-supervised by Prof. Shu Wu and Prof. Qiang Liu.
Previously, I had the privilege of visiting the National University of Singapore (NUS) as a PhD student, working with ZhangLab under the supervision of Prof. Yang Zhang and the mentorship of Dr. Zhiyuan Liu.
On the industry side, I have been fortunate to intern at DP Technology and Alibaba DAMO Academy (supervised by Dr. Yu Rong), as well as at Bytedance and Meituan. I received a B.E. in Software Engineering from Tongji University.
📍 Feel free to reach out if you are interested in my work or would like to get in touch with me.
Google Scholar /
Github /
CV[PDF]
Email: wangliang.leon20[at]gmail.com
Research Interests
As AI advances at a breathtaking pace and we edge ever closer to AGI, I am deeply excited by the convergence of generative AI and agentic AI with the life science. My research is driven by the vision of enabling machines to understand the language of life and accelerate drug discovery, spanning the following areas:
- AI for Life Science and Drug Discovery Understanding small molecules, biomolecules (proteins, RNA, DNA), and their interactions, ultimately enabling their rational design.
- Generative AI Training and sampling paradigms for diffusion models, flow matching, and diffusion language models (masked diffusion models), with application to scientific problems.
- Agentic AI Cornerstones of LLM-driven AI agents, including reasoning capabilities and harness engineering, and their application to scientific discovery.
Previously, I also worked on graph machine learning and data mining.
News
[Jan 26, 2025] One paper on molecular structure elucidation (SpectraLLM) is accepted by ICLR 2026! [Sep 20, 2025] Two papers on enzyme design (EnzyControl) and molecular representation pre-training (3D-GSRD) are accepted by NeurIPS 2025! [Jul 10, 2025] Our paper "DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models" is released on arXiv! [Paper][Code] [May 26, 2025] Our survey paper "Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey" is released on arXiv! [Paper] [Awesome Paper List] [Apr 17, 2025] I will attend ICLR 2025 from Apr 24 to Apr 28. Looking forward to seeing you in Singapore! [Feb 14, 2025] Our survey paper "Diffusion Models for Molecules: A Survey of Methods and Tasks" is released on arXiv! [Paper] [Awesome Paper List] [Jan 23, 2025] One paper on molecular representation pre-training (MolSpectra) is accepted by ICLR 2025! [Dec 10, 2024] One paper on knowledge graph completion (S2DN) is accepted by AAAI 2025! [Dec 9, 2024] I will attend NeurIPS 2024 from Dec 10 to Dec 15. Looking forward to seeing you in Vancouver@Canada! [Nov 1, 2024] Invited to give a talk on molecular representation learning and property prediction at DP Technology. [Slides] [Sep 26, 2024] One paper on molecular property prediction (Pin-Tuning) is accepted by NeurIPS 2024!
Selected Publications
(Full Publication List)AI for Science
SpectraLLM: Uncovering the Ability of LLMs for Molecule Structure Elucidation from Multi-Spectral Data
Yunyue Su, Jiahui Chen, Zao Jiang, Zhenyi Zhong, Liang Wang, Qiang Liu, Zhaoxiang Zhang
ICLR 2026
[Paper] [Code] EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation
Chao Song, Zhiyuan Liu, Han Huang, Liang Wang, Qiong Wang, Jianyu Shi, Hui Yu, Yihang Zhou, Yang Zhang
NeurIPS 2025
[Paper] [Code] 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
Chang Wu, Zhiyuan Liu, Wen Shu, Liang Wang, Yanchen Luo, Wenqiang Lei, Yatao Bian, Junfeng Fang, Xiang Wang
NeurIPS 2025
[Paper] [Code] MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra
Liang Wang, Shaozhen Liu, Yu Rong, Deli Zhao, Qiang Liu, Shu Wu, Liang Wang
ICLR 2025
[Paper] [Code] [Poster] [Slides] [Blog (Chinese)] Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
Liang Wang, Qiang Liu, Shaozhen Liu, Xin Sun, Shu Wu, Liang Wang
NeurIPS 2024
[Paper] [Code] [Poster]
Graph Machine Learning
Rethinking Graph Masked Autoencoders through Alignment and Uniformity
Liang Wang*, Xiang Tao*, Qiang Liu, Shu Wu, Liang Wang
AAAI 2024
[Paper] [Code] [Poster] DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization
Xin Sun, Liang Wang, Qiang Liu, Shu Wu, Zilei Wang, Liang Wang
KDD 2024
[Paper] GSLB: The Graph Structure Learning Benchmark
Zhixun Li, Liang Wang, Xin Sun, Yifan Luo, Yanqiao Zhu, Dingshuo Chen, Yingtao Luo, Xiangxin Zhou, Qiang Liu, Shu Wu, Liang Wang, Jeffrey Xu Yu
NeurIPS 2023
[Paper] [Code]
Data Mining
S2DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion
Tengfei Ma, Yujie Chen, Liang Wang, Xuan Lin, Bosheng Song, Xiangxiang Zeng
AAAI 2025
[Paper] Bi-Level Graph Structure Learning for Next POI Recommendation
Liang Wang, Shu Wu, Qiang Liu, Yanqiao Zhu, Xiang Tao, Mengdi Zhang, Liang Wang
IEEE Transactions on Knowledge and Data Engineering 2024
[Paper] [Code] Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection
Xiang Tao, Liang Wang, Qiang Liu, Shu Wu, Liang Wang
WWW 2024
[Paper]
Preprints
DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models
Liang Wang, Yu Rong, Tingyang Xu, Zhenyi Zhong, Zhiyuan Liu, Pengju Wang, Deli Zhao, Qiang Liu, Shu Wu, Liang Wang, Yang Zhang
arXiv preprint 2025
[Paper] [Code] [Model Checkpoints] [Datasets] Diffusion Models for Molecules: A Survey of Methods and Tasks
Liang Wang, Chao Song, Zhiyuan Liu, Yu Rong, Qiang Liu, Shu Wu, Liang Wang
arXiv preprint 2025
[Paper] [Awesome Paper List] Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey
Zhixun Li*, Bin Cao*, Rui Jiao*, Liang Wang*, Ding Wang, Yang Liu, Dingshuo Chen, Jia Li, Qiang Liu, Yu Rong, Liang Wang, Tong-yi Zhang, Jeffrey Xu Yu
arXiv preprint 2025
[Paper] [Awesome Paper List] A Survey of Graph Transformers: Architectures, Theories and Applications
Chaohao Yuan, Kangfei Zhao, Ercan Engin Kuruoglu, Liang Wang, Tingyang Xu, Wenbing Huang, Deli Zhao, Hong Cheng, Yu Rong
arXiv preprint 2025
[Paper]
Projects
PyGCL: An easy-to-use library for graph contrastive learning with PyTorch. It implements a wide variety of contrastive objectives, data augmentations, contrasting modes and other utilities useful for implementing and evaluating contrastive learning on graphs.
GSLB: An open-source library built for easy implementation and evaluation of graph structure learning model family. It offers a versatile control of graph dataset loading, structure learners, structure processors, and a bunch of reproduced models.
Services
Conference Reviewer
Conference on Neural Information Processing Systems (NeurIPS), 2024, 2025 International Conference on Learning Representations (ICLR), 2025, 2026 International Conference on Machine Learning (ICML), 2025, 2026 ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024, 2025, 2026 AAAI Conference on Artificial Intelligence (AAAI), 2026 International Conference on Artificial Intelligence and Statistics (AISTATS), 2025, 2026
Journal Reviewer
IEEE Transactions on Knowledge and Data Engineering (TKDE) IEEE Transactions on Computational Biology and Bioinformatics (TCBB)
Education
PhD (selected for the PhD honors program)
at Institute of Automation, Chinese Academy of Sciences
2021 - 2026 (Expected)
Major: Pattern Recognition and Intelligent Systems
Visiting PhD
at National University of Singapore
2025 - 2026
Research Interests: AI for Life Science, Generative AI, Agentic AI
Bachelor
at Tongji University
2017 - 2021
Major: Software Engineering
