Modern artificial intelligence (AI) increasingly relies on combining multiple sources of information, such as sound, motion, images, and sensor data, to achieve robust and intelligent behaviour. However, most existing multimodal AI systems depend on large, computationally intensive models that are difficult to deploy in settings with limited resources. This PhD project explores a different question: how can multimodal intelligence be achieved using minimal, efficient representations under resource constraints?
The project will investigate Tiny Multimodal Learning, a research direction focused on understanding what is essential for multimodal learning when computation, memory, or energy are limited. Rather than scaling up models, the research aims to identify principled, lightweight methods for representing and combining multimodal information over time. Grounded in machine learning, representation learning, and efficient algorithms, the work addresses real-world challenges in sustainable and accessible AI.
As a PhD researcher, you will gain experience in multimodal machine learning, experimental benchmarking, and algorithmic design, with opportunities to explore connections to dynamical systems and efficient model architectures. You will work in a supportive, inclusive doctoral environment, with access to strong research facilities, interdisciplinary collaboration, training in research and professional skills, and opportunities to publish at leading international venues.
Objectives
The aim of this project is to develop principled and efficient methods for multimodal learning under resource constraints. The research seeks to understand how different types of data—such as audio, motion, images and sensor signals—can be combined using minimal representations without relying on large, computationally intensive models.
Key objectives include:
- Reviewing and benchmarking existing multimodal learning approaches under limited computational resources
- Investigating lightweight representations and fusion strategies for multimodal data
- Studying how temporal structure and missing data affect multimodal learning
- Identifying fundamental trade-offs between accuracy, efficiency, and robustness.
Funding
This studentship is open to home and international applicants. Home and international tuition fees will be covered for the duration of the 3-year award.
The student will receive a standard stipend payment for the duration of the award. The stipend rate is determined by the UKRI, currently £21,805 for the academic year 2026/27.
Candidate requirements
Essential
- A first-class or upper second-class (2:1) Bachelor’s degree or a Master’s degree (or equivalent), in Computer Science, Artificial Intelligence, Machine Learning, or a closely related discipline.
- A strong foundation in programming (e.g. Python) and core concepts in machine learning/data analysis.
- Ability to engage with research literature and develop analytical, problem-solving, and algorithmic thinking skills.
- Good written and verbal communication skills; ability to work both independently and collaboratively.
Desirable
- Experience with deep learning (frameworks like PyTorch or TensorFlow), multimodal data analysis.
How to apply
Please contact Professor Liangxiu Han with any questions.
To apply, please complete the online application form for a full-time PhD in Computing & Digital Technology. Please note, you are not required to submit a research proposal.
Please complete the Doctoral Project Applicant Form; include your CV and a covering letter to demonstrate how your skills and experience map to the aims/objectives of the project, the area of research and why you see this area as being of importance/interest.
Please upload these documents in the supporting documents section of the University’s Admissions Portal or email the requested documents to pgradmissions@mmu.ac.uk.
Expected start date: October 2027.
Quote the reference: SciEng-LH-2027-28-Tiny Multimodal Learning
