Æß²ÊÖ±²¥

I am a Senior Lecturer in Games and Artificial Intelligence at Æß²ÊÖ±²¥, specialising in Computer Vision, Generative AI, Large Language Models (LLMs), and 3D Vision. My research explores state-of-the-art AI and deep learning methods, including diffusion models, GANs, and multimodal AI, with applications in games, immersive environments, digital twins, and intelligent systems.

My work focuses on developing scalable and high-performance AI systems for real-world and interactive applications, and I contribute to doctoral supervision and interdisciplinary research at the intersection of games and Artificial Intelligence.

Institute of Artificial Intelligence (IAI)

My research focuses on Computer Vision, Generative AI, Large Language Models (LLMs), 3D Scene Understanding, and Machine Learning, with applications in intelligent visual systems, healthcare AI, and immersive technologies.

I develop scalable, interpretable, and high-performance AI models across the following areas:

• 3D Vision and Scene Understanding – point cloud processing, neural radiance fields (NeRF), and Gaussian splatting for photorealistic 3D reconstruction and rendering.

• Computer Vision – image understanding, object detection, semantic segmentation, and depth estimation for spatial intelligence.

• Multimodal AI and Vision-Language Models – integration of vision and language models (e.g. CLIP, BLIP, Flamingo, and LLM-based frameworks) for cross-modal reasoning and grounded AI systems.

• Large Language Models (LLMs) – efficient fine-tuning, multimodal extension, and integration with vision systems for reasoning, automation, and intelligent agents.

• Generative Adversarial Networks (GANs) – image synthesis, style transfer, data augmentation, and domain adaptation, including applications in medical imaging.

• Diffusion Models – next-generation generative architectures for high-fidelity image, video, and 3D content generation.

This work advances state-of-the-art research in Computer Vision, Generative AI, and LLM-driven intelligent systems, with a focus on real-world deployment and scalable AI solutions.

My research utilises frameworks such as PyTorch, TensorFlow, CUDA, and GPU-accelerated computing, supporting efficient experimentation and large-scale model development.

---

PhD Supervision

I supervise PhD research in Computer Vision, Generative AI, Large Language Models (LLMs), Multimodal AI, and 3D Scene Understanding.

I welcome enquiries from highly motivated candidates with a strong background in Artificial Intelligence, Machine Learning, Computer Science, or related disciplines.

Projects may be undertaken through self-funded, externally funded (e.g. government or industry), or collaborative routes, depending on alignment with ongoing research and funding opportunities, including UKRI, EPSRC, and Horizon Europe.

Prospective applicants are encouraged to make initial contact to discuss potential research directions.

I am a recognised PhD supervisor within the Æß²ÊÖ±²¥ Doctoral College, and my profile can be found by searching for my name on the university’s doctoral supervisor directory. I particularly welcome enquiries from candidates interested in innovative research at the intersection of Generative AI, Computer Vision, and Large Language Models, especially in real-world and interactive systems.

---

 Collaborations and Research Alignment

My research is well aligned with the funding and collaboration priorities of UKRI (EPSRC), Innovate UK, and Horizon Europe in Generative AI, Large Language Models, and data-driven intelligent systems. I welcome opportunities for academic and industry collaboration in these areas.

---

Research Areas and Expertise

Computer Vision, Generative AI, Machine Learning, Large Language Models (LLMs), Multimodal AI, 3D Vision, Diffusion Models, GANs, Neural Radiance Fields (NeRF), Gaussian Splatting, Vision-Language Models, AI for Healthcare

I teach across core and advanced topics in Artificial Intelligence, Machine Learning, and Computer Science, with a focus on real-world applications and scalable systems:

• • Computer Vision – fundamentals of visual perception, image understanding, object detection, semantic segmentation, and scene understanding for intelligent systems

  • Machine Learning – supervised, unsupervised, and reinforcement learning algorithms, with applications in data-driven modelling and predictive analytics

  • Deep Learning – neural network architectures including CNNs, RNNs, and Transformers, along with optimisation techniques and model evaluation

  • Generative AI – principles and applications of GANs, diffusion models, and autoencoders for image, video, and content generation

  • 3D Vision and Computer Graphics – point cloud processing, depth estimation, Neural Radiance Fields (NeRF), and Gaussian splatting for 3D reconstruction and rendering

  • Multimodal AI – integration of visual, textual, and auditory data for cross-modal understanding, reasoning, and generative systems

  • Parallel and Distributed Computing – CUDA programming, GPU acceleration, and parallel algorithms for large-scale AI and deep learning workloads

PhD in Computer Science and Engineering.

• Agent-Based Modelling and Parallel Computing
• Neural Systems
• Generative Adversarial Networks for Computational Imaging
• Introduction to Neuromorphic Computing
• Reinforcement Learning
• Artificial Neural Networks
• Deep Learning
• Artificial Intelligence
• Machine Learning

• Fellow of Innovation in Science Pursuit for Inspired Research (INSPIRE)
• University Gold Medalist

• Lifetime Member, ISTE - Indian Society for Technical Education (ISTE)
• Institute of Electrical and Electronics Engineers

• EMC2 Academic Associate, Data Science, and Big Data Analytics
• National Eligibility Test (UGC‑NET) for Lectureship

0000-0001-6227-0733