Haiteng Zhao
Fifth-year Ph.D student, Peking University
zhaohaiteng [AT] pku.edu.cn
Bio
I am a fifth-year Ph.D. student in the Department of Machine Intelligence at Peking University. Currently, I am conducting research at Sigma Lab, Peking University, supervised by Prof. Zhihong Deng. I am also working at the University of Hong Kong with Lingpeng Kong and Qi Liu on many exciting projects.
Previously, I attained a B.Sc. degree in Psychology from Peking University. My current focus lies in exploring whether deep learning can effectively encode human-like intelligence, encompassing transfer, generalization, reasoning and planning capacities, and more.
As a researcher, I focus on various aspects of deep learning. My work primarily spans three key areas:
- Machine Learning Theory: Investigating topics such as generalization theory, domain adaptation, transfer learning, and robustness.
- Structured Data Understanding: Exploring how deep models can effectively handle structured problems, including understanding structured data and knowledge, solving symbolic problems, and more. My current research in this area emphasizes AI for Science (AI4Science).
- Reasoning and Planning: Addressing compositional generalization challenges in deep models, which are crucial for achieving human-like intelligence.
I look forward to chatting and collaborating with you!
Publications
Most recent publications on Google Scholar.
‡ indicates equal contribution.
Non-myopic Generation of Language Model for Reasoning and Planning
Chang Ma, Haiteng Zhao, Junlei Zhang, Junxian He, Lingpeng Kong
arXiv preprint
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
Yuran Xiang, Haiteng Zhao, Chang Ma, Zhi-Hong Deng
arXiv preprint
Empowering Large Language Model Agents through Action Learning
Haiteng Zhao, Chang Ma, Guoyin Wang, Jing Su, Lingpeng Kong, Jingjing Xu, Zhi-Hong Deng, Hongxia Yang
Conference on Language Modeling (COLM) 2024
Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning
Yiqi Wang, Wentao Chen, Xiaotian Han, Xudong Lin, Haiteng Zhao, Yongfei Liu, Bohan Zhai, Jianbo Yuan, Quanzeng You, Hongxia Yang
arXiv preprint
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
Haiteng Zhao, Shengchao Liu, Chang Ma, Hannan Xu, Jie Fu, Zhi-Hong Deng, Lingpeng Kong, Qi Liu
Conference on Neural Information Processing Systems (NeurIPS) 2023
ChatPathway: Conversational Large Language Models for Biology Pathway Detection
Yanjing Li, Hannan Xu, Haiteng Zhao, Hongyu Guo, Shengchao Liu
Conference on Neural Information Processing Systems (NeurIPS) 2023 AI for Science Workshop
Are More Layers Beneficial to Graph Transformers?
Haiteng Zhao, Shuming Ma, Dongdong Zhang, Zhi-Hong Deng, Furu Wei
International Conference on Learning Representations (ICLR) 2023
Retrieved Sequence Augmentation for Protein Representation Learning
Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Lingpeng Kong
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024
Certified Robustness Against Natural Language Attacks by Causal Intervention
Haiteng Zhao‡, Chang Ma‡, Xinshuai Dong‡, Anh Tuan Luu, Zhi-Hong Deng, Hanwang Zhang
International Conference on Machine Learning (ICML) 2022
Domain Adaptation via Mutual Information Maximization
Haiteng Zhao, Chang Ma, Qinyu Chen, Zhihong Deng
International Joint Conference on Artificial Intelligence (IJCAI) 2022 (Long presentation)
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
Yuran Xiang, Haiteng Zhao, Chang Ma, Zhi-Hong Deng
arXiv preprint
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
Haiteng Zhao, Shengchao Liu, Chang Ma, Hannan Xu, Jie Fu, Zhi-Hong Deng, Lingpeng Kong, Qi Liu
Conference on Neural Information Processing Systems (NeurIPS) 2023
ChatPathway: Conversational Large Language Models for Biology Pathway Detection
Yanjing Li, Hannan Xu, Haiteng Zhao, Hongyu Guo, Shengchao Liu
Conference on Neural Information Processing Systems (NeurIPS) 2023 AI for Science Workshop
Retrieved Sequence Augmentation for Protein Representation Learning
Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Lingpeng Kong
Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024
Non-myopic Generation of Language Model for Reasoning and Planning
Chang Ma, Haiteng Zhao, Junlei Zhang, Junxian He, Lingpeng Kong
arXiv preprint
Empowering Large Language Model Agents through Action Learning
Haiteng Zhao, Chang Ma, Guoyin Wang, Jing Su, Lingpeng Kong, Jingjing Xu, Zhi-Hong Deng, Hongxia Yang
Conference on Language Modeling (COLM) 2024
Are More Layers Beneficial to Graph Transformers?
Haiteng Zhao, Shuming Ma, Dongdong Zhang, Zhi-Hong Deng, Furu Wei
International Conference on Learning Representations (ICLR) 2023
Certified Robustness Against Natural Language Attacks by Causal Intervention
Haiteng Zhao‡, Chang Ma‡, Xinshuai Dong‡, Anh Tuan Luu, Zhi-Hong Deng, Hanwang Zhang
International Conference on Machine Learning (ICML) 2022
Domain Adaptation via Mutual Information Maximization
Haiteng Zhao, Chang Ma, Qinyu Chen, Zhihong Deng
International Joint Conference on Artificial Intelligence (IJCAI) 2022 (Long presentation)
Vitæ
Full Resume in PDF.
-
Tencent Mar 2024 -Research Intern
AI Lab NLP -
Bytedance Aug 2023 - Feb 2024Research Intern
Data-AML-US -
The University of Hong Kong Sep 2022 -Research Intern
HKU NLP -
Microsoft Research Asia Jan 2022 - Oct 2022Research Intern
Natural Language Computing (NLC) group -
Nanyang Technological University June 2021 -Collaborator
NAIL Group, NLP -
Peking University Sep 2020 -Ph.D. Student
CS, Machine Learning -
Peking University July 2018 - July 2020Research Assistant
Sigma Lab, Department of Machine Intelligence -
Peking University Sep 2016 - July 2020B.Sc. Student
Psychology