Published four core A* conference papers at NeurIPS 2025, WWW 2025, and EMNLP 2024-25, along with two workshops at top-tier NLP conferences.
Sept 2025: Paper 'Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation' accepted at NeurIPS 2025.
Aug 2025: Paper 'M-Help on Mental Health Help-Seeking Behavior Detection' accepted at EMNLP 2025 Findings.
Jan 2025: Paper on multimodal detection of mental health disorders in social media accepted at TheWebConf (WWW) 2025.
Sept 2024: Paper 'LaRA on Cross modal LLM with speech' accepted at EMNLP 2024 Findings.
June 2024: Paper on Emotion recognition in multi-party conversations (code-mixed) and emotion trigger dynamics accepted at SemEval 2024 co-held with NAACL '24.
March 2024: Paper on Hate Speech Detection in Telugu-English Code-Mixed Text accepted at DravidianLangTech 2024 co-held with EACL '24.
Feb 2024: Team FeedForward secured 3rd place in Tasks 1 and 2, and 5th place in Task 3 of the SemEval 2024 EDIREF competition.
Research Experience
Was a research intern at Microsoft Research (MSR) India, FLaMe.nlp Research Lab, and LCS2 Lab at IIIT Delhi, India, under the mentorship of Dr. Md. Shad Akhtar.
Education
Completed undergraduate degree from Indian Institute of Information Technology (IIIT) Dharwad, India.
Background
Research interests lie at the intersection of Natural Language Processing (NLP), Multimodal Systems, and AI Safety. Working at MBZUAI under the guidance of Dr. Yova Kementchedjhieva.