Abdullah Mazhar

I am a Ph.D. Candidate at IIIT Delhi, working under the guidance of Dr. Md. Shad Akhtar at the FLaMe Lab. I completed my undergraduate degree in Computer Science and Engineering at the Institute of Engineering and Rural Technology (IERT), Allahabad, India. My research interests lie at the intersection of Natural Language Processing (NLP), Multimodal Systems, and Responsible AI for Mental Health. My research journey spans over two years, with publications including a Main Oral paper at ACL 2026, an Oral paper at The Web Conference (WWW) 2025, and in the Main Track of NeurIPS 2025. Previously, I worked as a Project Officer at IIT Madras, where I contributed to the Bhashini initiative by building end-to-end Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) pipelines for Indian languages. Before that, I worked as a Data Scientist at Birlasoft and a Software Developer at Analytics2AI.

To know more, refer to my resume or drop me an email!

April 2026: Our paper "Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation" has been accepted in the Main Track of ACL 2026 (ORAL).
Sep 2025: Our paper "Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation" has been accepted in the Main Track of NeurIPS 2025.
Aug 2025: Received Google Research Grant, Microsoft Research Grant, and ACM India Travel Grant to present our WWW 2025 paper in Sydney, Australia.
Jan 2025: Our paper AxiOM & M3H on multimodal understanding of mental health memes was accepted as an Oral paper at The Web Conference (ORAL) 2025.
Dec 2023: Started my Ph.D. in Computer Science at IIIT Delhi, advised by Dr. Md. Shad Akhtar.
Sep 2022: Joined IIT Madras as a Project Officer, contributing to the Bhashini initiative by building end-to-end ASR and TTS systems for Indian languages.
May 2021: Joined Birlasoft as a Data Scientist, where I worked on AI-driven insurance automation and customer support solutions until Sep 2022.

Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation
Abdullah Mazhar,Het Riteshkumar Shah , Aseem Srivastava, , Smriti Joshi, Md Shad Akhtar
ACL '26 | Main Track
paper code poster

Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
Zuhair Hasan Shaikh, Abdullah Mazhar, Aseem Srivastava, Md Shad Akhtar
NEURIPS '25 | Main Track
paper code poster

Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification
Abdullah Mazhar, Zuhair Hasan Shaikh, Aseem Srivastava, Polly Ruhnke, Lavanya Vaddavalli, Sri Keshav Katragadda, Shweta Yadav, Md Shad Akhtar
WWW '25 | Conference (A*) | The ACM Web Conference 2025 (Oral)
paper code poster

Ph.D. Candidate

IIIT Delhi · FLaMe Lab

Dec 2023 – Present · Delhi, India

Project Officer

IIT Madras

Sep 2022 – Dec 2023 · Chennai, India

Worked on the Bhashini initiative, building end-to-end ASR and TTS systems for Indian languages.

Data Scientist

Birlasoft Ltd.

May 2021 – Sep 2022 · Noida, India

Developed solutions for Insurance Claim Automation using Azure AI, Chatbots, and ML models.