Multimodal Understanding of Visual and Textual Information through Large Language Models for Advanced Cognitive Visual Tasks (PhD)

Program Overview

The program offers a unique interdisciplinary approach with potential applications in various fields, including healthcare, robotics, and content creation.

Program Outline

Research Directions:

• Multimodal representation learning: Develop methods for joint representation learning using LLMs and computer vision techniques.

Impact:

Develop a model with potential applications in healthcare, sports, robotics, content creation platforms, assistive technologies, and more. Evaluate the model's performance and scalability on benchmark datasets and explore potential industry collaborations.

Outline:

Course Schedule:

• First year: Master-level modules in advanced computer vision, natural language processing, and machine learning.
• Second year: Research-oriented modules focusing on multimodal representation learning, content generation, and semantic understanding.
• Third year: Thesis research under the supervision of faculty members.

Individual Modules:

• Advanced Computer Vision: Topics include deep learning architectures, object detection, image segmentation, and scene understanding.
• Natural Language Processing: Topics include NLP fundamentals, language modeling, and deep learning methods for NLP tasks.
• Machine Learning: Topics include supervised learning, unsupervised learning, reinforcement learning, and deep learning models.

Assessment:

Methods:

• Continuous assessment through coursework, assignments, and presentations.
• End-of-term exams for taught modules.
• Thesis assessment by a supervisor and an external examiner.

Criteria:

• Depth of understanding of relevant concepts and theories.
• Ability to apply knowledge to solve real-world problems.
• Critical thinking and analytical skills.
• Communication and presentation skills.
• Research skills and originality.

Teaching:

Teaching Methods:

• Lectures by faculty members and guest speakers.
• Laboratory sessions and practical exercises.
• Research seminars and workshops.
• Individual supervision and feedback.

Faculty:

• Prof. Baihua Li (primary supervisor)
• Strong research team with over 30 Ph.D. students, postdoctoral researchers, and academic staff in the AI and robotics research area.

Unique Approaches:

• Interdisciplinary approach that combines computer vision and natural language processing.
• Focus on research excellence and industry collaboration.
• Access to research facilities, high-spec computing resources, and the £5.8M DigLabs research initiative.

Careers:

Potential Career Paths:

• Research Scientist in AI, computer vision, or NLP.
• Robotics Engineer.
• Software Engineer focusing on image and video processing or natural language applications.
• Data Scientist with expertise in multimodal data analysis.
• Academic researcher in computer science or related fields.

Career Opportunities:

• Research positions in companies, universities, and research institutions globally.
• Opportunities in large technology companies working on AI and machine learning solutions.
• Potential to start your own company or pursue research in an academic setting.

Other:

• The Department of Computer Science at Loughborough University has an excellent research record in AI, machine learning, robotics, computer vision, and data science.
• The successful candidate will have access to robotics and AI laboratories, high-specification computing facilities (e.g., GPUs), HPC, and £5.8M DigLabs, complementing a £9m investment in research and teaching.
• Regular supervision meetings and collaboration opportunities with a strong AI research team.

UK fee: £4,712 Full-time degree per annum International fee: £26,000 Full-time degree per annum University fees and charges can be paid in advance and there are several methods of payment, including online payments and payment by instalment. Fees are reviewed annually and are likely to increase to take into account inflationary pressures.