Muhammad Ali Farooq

Currently I am working on Adapt project where my research work is related to curating complex multimodal synthetic datasets by using diffusion models, LLM's and GAN architecture.

The main objective is the development of a multimodal (sound and vision) AI processing platform with low cost and low power consumption to be used for the creation of voice-enabled devices and other real-world applications.

I have been working towards generating large scale synthetic human facial datasets using composite structure of computer vision algorithms which includes single domain Generative Adversarial Networks and multiple domain Generative Adversarial Networks for optimal training and validation of deep learning networks. Moreover, working towards augmenting medical datasets using text to image translation.

Further working on model optimization using state-of-the-art network quantization methods for deployment on single board low powered edge devices for real-time data processing.

Previously I am working on Disruptive Technologies Innovation Fund ‘DTIF-DAVID’ project funded by Enterprise Ireland (EI).

Google Scholar Profile

Linkedin Profile