Jayneel Parekh — AI Researcher

I am a Machine Learning/Deep Learning/AI Researcher at ISIR, Sorbonne University (2023-Current) with Prof. Matthieu Cord, working on understanding and controlling Multimodal LLMs (vision/text) through their internal representations. Before that, I was a PhD student at LTCI, Télécom Paris, Institut Polytechnique de Paris (2019-2023) under the supervision of Prof. Florence d'Alché and Prof. Pavlo Mozharovskyi, on the topic of interpretability of neural networks, applied on image or audio data. I completed my undergrad studies (B.Tech + M.Tech) in Electrical Engineering at IIT Bombay (2014-2019) with focus on Signal Processing, where I worked with Prof. Preeti Rao and Prof. Yi-Hsuan Yang on converting an input speech to singing output following a given melody. I am interested by a wide variety of representation learning tasks applied to audio/visual/multimodal domains or current generative models, including understanding their internals or controlling their outputs.

Stackforce AI infers this person is a Machine Learning Researcher specializing in AI and audio processing technologies.

Experience: 7 yrs 3 mos