Our research group are actively recruiting self-motivated Postdoc, Ph.D. students, Dual PhD Degree students, MPhil/Msc, and Research Assistants, etc. Visiting scholars, interns, and self-funded students are also welcome. Please refer to this section for more detail. Send me an email if you are interested.
Dr. Changmeng Zheng
Research Assistant Professor
News
2024.10: Our paper "A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning" has been nominated as Best Paper Award in ACM Multimedia 2024! Congratulations to all co-authors.
2024.07: One paper on Multimodal Reasoning is accepted by ACM Multimedia 2024.
2023.05: Two papers on Relation Extraction and Scene Graph Generation are accepted by IEEE TCSVT.
2023.05: Two paper on Multimodal Entity and Relation Extraction is accepted by ACL 2023.
Research Outline
I am generally interested in multimodal large language models, knowledge graphs and social media analytics. In particular, my research
focuses on the extraction, retrieval and question-answering of text, video, and live media arising from the web and social
networks. Apart from that, I have also extensively explored interdisciplinary areas and applications of artificial
intelligence, including but not limited to: medical data analysis, marine trajectory prediction and desktop application visualization.
My research addresses the challenges of fine-grained reasoning and hallucination in MLLMs by exploring innovative approaches through multi-agent collaborative frameworks and knowledge-augmented architectures.
I'm interested in empowering current deep learning systems through structured knowledge representations, facilitating robust cross-modal reasoning and enabling seamless connections across diverse modalities.
My research focuses on developing deep learning approaches to multimodal data analysis, bridging diverse disciplines to solve complex real-world problems through the integration of multiple data types and domain knowledge..
Services
I'm excited to serve the research community in various aspects.
I served as committee members for AI conferences including ACL, EMNLP, AAAI, IJCAI and ACM MM for over 5 years, and I'm serving as the journal reviewer for IEEE TASLP, TIP, TCSVT, TAI, TCSS and TCDS.
In addition, I lead or participate many national funding projects like China National Programs for Science and Technology, China National Natural Science Foundation and the Major Research Project in Guangzhou City, collaborating with Peng Cheng Lab, Kingsoft and TCL.
A few selected publications are listed for each research direction. See Google Scholar
for a full list of publications.
Most of the algorithms developed are incorporated into my Github repository.
Multimodal Representation Learning and Alignment
I work on representation learning and alignment of multiple modalities via structured knowledge.
Unsupervised entity-aware adversarial training relieves domain divergence in NER.
ACL 2020
Dual channel graph captures the object and syntactic relations simultaneously.
ACL 2023 Findings
Contrastive learning can refine the original representations of entities in different domains.
Interdisciplinary Applications
My research encompasses diverse interdisciplinary applications of artificial intelligence, with particular emphasis on healthcare analytics, maritime intelligence and software engineering.
CEP scheme and DCEP scheme, to improve the topic coherence by incorporating the concept information of the entities.
APWeb 2021
Cross-modality adversarial training and modality-invariant attention bring better semantic alignment for VQA.
ICME 2021
The first multimodal relation extraction dataset consisting of 10000+ sentences on 31 relations derived from Twitter.
Openings
For prospective students, I appreciate reading the following before reaching out to me through email.
To make it easier for me to identify the applications, use "PhD (or Research Assistant , Visiting Student) Application" as your title.
PhDs
When reaching out to me, in addition to your CV, it would be best to demonstrate the following in your email.
Applicants do not need to have a degree in computer science, but they should possess good coding skills and a basic understanding of natural language processing. The research direction of the applicants does not need to align with mine, as long as they have sufficient interest in large language models.
Prospective students are encouraged to visit our laboratory in advance to gain a better understanding of how our lab operates. This will facilitate a more informed decision based on mutual selection principles.
Students who have only one publication as a (co-)first author, demonstrating their ability to develop ideas, implement, analyze, and write papers, are often considered more favorably than those who have participated in numerous publications without leading these projects.
Note:
I am aware that many students without a first-author publication record are interested in applying to our lab. We welcome these students to participate in our publication-oriented projects or lead one influential open-source project. We are looking for self-motivated students. I will guide you in advancing these projects, and strong performance will significantly enhance your chances of a successful application.
Research Assistants/Visiting Students
I welcome research assistants, visiting students, and interns at all levels. Students are required to demonstrate a strong interest and good background knowledge in large language models. While prior research experience is encouraged, it is not mandatory.
All positions for research assistants, visiting students, and internships can be remote. Research assistant positions will be compensated according to the applicant's background.
Contact
Location
I'm currently located at Mong Man Wai Building,
The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong
Email
You could reach me via email.
Show Email
I will try my best to respond if the schedule permits, unless I'm overwhelmed by emails.
