PhD Studentship: Tiny Multimodal Learning Under Resource Constraints

Project advert

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.

Project aims and objectives

The aim of this PhD 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.

The project emphasises foundational machine learning research while maintaining strong relevance to real-world, resource-aware AI systems.

Funding

Both Home and International students can apply. Only home tuition fees will be covered for the duration of the 3-year award, which is £5,006 for the year 2025/26. Eligible international students will need to make up the difference in tuition fee funding (Band 2 for the year 2025/26).

The student will receive a standard stipend payment for the duration of the award. These payments are set at a level determined by the UKRI, currently £20,780 for the academic year 2025/26.

Specific requirements of the candidate

Essential Requirements:

• 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 or data analysis.
• Ability to engage with research literature and develop analytical, problem-solving, and algorithmic thinking skills.
• Good written and verbal communication skills, and the ability to work both independently and collaboratively.

How to apply

Interested applicants should contact Liangxiu Han for an informal discussion. 

To apply you will need to complete the online application form for a full time PhD in Computing & Digital Technology

Please complete the Doctoral Project Applicant Form, and include your CV and a covering letter to demonstrate how your skills and experience map to the aims and objectives of the project, the area of research and why you see this area as being of importance and interest. 

Please upload these documents in the supporting documents section of the University’s Admissions Portal.

Applications closing date: 16 March 2026 

Expected start date: 1 October 2026

Please quote the reference: SciEng-LH-2026-27-Tiny Multimodal Learning

Advert information