Led by Dr. Sriparna Saha

Drisha Lab

Researching intelligent systems that can see, read, reason, and communicate across language, vision, and real-world data.

Meet the Lab Explore Research

About the lab

Multimodal Information Processing Lab

DRISHA Lab (IIT Patna), under the guidance of Prof. Sriparna Saha, is dedicated to advancing multimodal information processing and multilingual AI. Our research encompasses language model reasoning, multimodal summarization, healthcare AI, misinformation detection, recommendation systems, financial AI, and culturally aware language technologies. We strive to develop inclusive, responsible, and socially impactful AI that empowers diverse languages, regions, and communities.

—Current/Registered PhD Scholars

—Graduated PhD Scholars

—Active Projects

Research themes

What we work on

Research page

Vision-Language Intelligence

Image/video understanding, visual grounding, captioning, and multimodal reasoning.

Natural Language Processing

Multilingual NLP, dialogue, information extraction, summarization, and language generation.

Responsible and Explainable AI

Interpretable, reliable, and human-centered models for real-world use.

AI for Society

Sports, healthcare, education, and industry collaborations with measurable impact.