I am currently a Research Scientist at ADIA Lab, Abu Dhabi, UAE. I am majorly working on agent reasoning and planning in sandbox environment setups.
Prior to this, I completed my Postdoctoral Research at TU Berlin, Germany, under the supervision of Prof. Fatma Deniz, where I worked on understanding bilingual language processing in the human brain and multilingual language models.
I completed my PhD in Computer Science at Inria, I was supervised by Dr. Xavier Hinaut and Prof. Alexandre Frederic. During my Ph.D, I also spent time as a visiting scholar at MaxPlanck Institute for Software Systems (MPI-SWS), Germany, where I was supervised by Dr. Mariya Toneva. My main research interests are at the Bridging AI and Neuroscience (Neuro-AI), Language Analysis in the Brain and Language Models, Multimodal brain alignment with multimodal models, and Mechanistic interpretability of language models.
Prior to that, I was a Lead Data Scientist at Woundtech Innovative Healthcare Solutions, where I worked on AI-driven solutions for automated wound assessment, patient risk of hospitalization, wound image segmentation and NLP-based document processing to enhance clinician decision-making. Before that, I was a Data Scientist at Teradata R&D, where I worked on NLP, text analytics, machine learning, and graph analytics to enhance Teradata Aster’s AI/ML capabilities.
Our paper featured by EqualyzAI on Twitter
'How much AI do we really need to mirror the human brain? 3B-parameter models can predict brain activity about as well as much larger 14B models — brain alignment saturates at modest model sizes.' - EqualyzAI
Tutorial: Encoding and Decoding Language in the Brain with Language Models
has been accepted to EACL 2026! (A)
EACL 2026
Nov 07, 2025
Aligning Text/Speech Representations from Multimodal Models with MEG Brain Activity During Listening
has been selected for SAC Highlight Award (Top 2% of accepted papers)
EMNLP 2025
Aligning Text/Speech Representations from Multimodal Models with MEG Brain Activity During Listening
has been accepted to EMNLP Conference 2025 (Main, Long, A*) (Nominated for the Paper Award)
EMNLP 2025
