Multimodal Learning
Joint modeling of text, images, video, and structured signals for richer understanding.
Research
Building AI that connects language, vision, and decisions
Our work spans foundational methods and applied systems, with an emphasis on robust models, explainability, and Indian language and societal contexts.
Natural Language Processing
Multilingual NLP, dialogue systems, information extraction, summarization, and language generation.
Computer Vision
Visual recognition, grounding, captioning, and vision-language interaction.
Explainable and Responsible AI
Trustworthy AI systems with interpretability, fairness, and human-centered evaluation.
AI for Sports and Society
Real-time multilingual AI agents, analytics, and assistive systems for practical impact.
Industry Collaboration
Research translation with partners in analytics, advisory, and applied AI.
Current Projects