Current systems focus on transmitting bits accurately. This project explores a meaning-first paradigm shift. You will develop a system where the transmitter uses deep generative models (DGMs) to extract and transmit compact semantic descriptors (latent representations) rather than raw data blocks. You will implement latent diffusion models to reconstruct high-fidelity data with unprecedented efficiency at the receiver. This method enables extreme compression ratios which facilitates ultra-high-rate experiences like 8K streaming or immersive XR over noisy, bandwidth-constrained channels.
By leveraging the inherent denoising capabilities of diffusion processes, you will design end-to-end Joint Source-Channel Coding (JSCC) architectures using state-of-the-art AI. You will validate these algorithms using software defined radios (SDRs), and prove their viability in real-world 6G environments.
We are looking for a bright, motivated student with a strong background in Computer Science, Electronic Engineering, or Applied Mathematics. You should possess a passion for Deep Learning (PyTorch/TensorFlow) and a robust understanding of signal processing or information theory.
Research Focus: AI-Native 6G, Semantic AI, Diffusion Models.
Key Skills: Machine Learning, Python, Wireless Theory.
Join us at the forefront of the next telecommunications revolution. By moving from sending bit to sending ideas, you will build the intelligent, generative networks of the future.
The School of Computing Sciences (https://www.uea.ac.uk/about/school-of-computing-sciences) provides a vibrant research environment for conducting Computing and allied research and training. We collaborate with multi-national companies such as Apple, BT, the National Trust and Aviva, research institutes in the Norwich Research Park (https://www.norwichresearchpark.com), as well as other universities and industries in the UK and overseas. We are also members of the Turing University Network, a group of 65 UK universities working together to advance world-class research and build skills for the future.
The successful candidate will also be expected to contribute to Tutor activities for laboratory support on our BSc and MSc Courses in Artificial Intelligence, Data Science, Computing Sciences and Cyber Security commensurate with their core expertise, within the working hours permitted for full-time Postgraduate Researchers.
Funding Notes
This PhD project is in a competition for a Faculty of Science funded studentship. Funding is available to UK applicants and comprises ‘home’ tuition fees, an annual stipend for 3 years and a research training support budget.
