Indian Institute of Information Technology Allahabad
The manuscript titled "PULSE: A Multi-Stage Artificial Intelligence Framework for Analyzing Vaccine Hesitancy on Twitter Using Particle Swarm Optimization and Large Language Models" has been accepted for publication in Swarm and Evolutionary Computation (h5-index: 74, Impact Factor: 8.5).
Read moreThe AICTE-QIP-PG Certificate Program 2025 on “From AI to Generative AI: Unlocking the Power of Smart Technologies” is a specialized training initiative designed to equip participants with foundational to advanced knowledge of Artificial Intelligence, Machine Learning, and Generative AI.
Read moreSix research papers from IRIS Lab have been accepted for presentation at IEEE TENCON 2026, to be held in Bali, Indonesia, from 10–13 October 2026. The accepted works span LLMs, multimodal AI, explainable AI, legal AI, healthcare AI, adversarial ML, swarm intelligence, and responsible AI.
Read moreThe manuscript titled "PULSE: A Multi-Stage Artificial Intelligence Framework for Analyzing Vaccine Hesitancy on Twitter Using Particle Swarm Optimization and Large Language Models" has been accepted for publication in Swarm and Evolutionary Computation (h5-index: 74, Impact Factor: 8.5).
Read moreThe AICTE-QIP-PG Certificate Program 2025 on “From AI to Generative AI: Unlocking the Power of Smart Technologies” is a specialized training initiative designed to equip participants with foundational to advanced knowledge of Artificial Intelligence, Machine Learning, and Generative AI.
Read moreSix research papers from IRIS Lab have been accepted for presentation at IEEE TENCON 2026, to be held in Bali, Indonesia, from 10–13 October 2026. The accepted works span LLMs, multimodal AI, explainable AI, legal AI, healthcare AI, adversarial ML, swarm intelligence, and responsible AI.
Read moreThe Information Retrieval & Intelligent Semantics (IRIS) Lab in the Department of Information Technology at IIIT Allahabad serves as a focused and dynamic research environment dedicated to addressing cutting-edge challenges in Multilingual, Cross-lingual, and Multimodal Natural Language Processing, Information Retrieval, Computational Biology, Health Informatics, and Artificial Intelligence.
The lab actively explores emerging paradigms such as Generative AI, Agentic AI, and Trustworthy AI, with an emphasis on building robust, scalable, interpretable, and ethically grounded intelligent systems.
The vision of IRIS Lab is to foster inclusive, intelligent, and socially responsible AI technologies that advance fundamental research while delivering meaningful real-world impact. By prioritizing multilingual and cross-lingual intelligence, the lab aims to bridge linguistic and cultural divides, enabling AI systems that are accessible and effective across diverse populations and low-resource settings.
A major thrust of the lab lies in interdisciplinary and application-driven research. In Computational Biology and Health Informatics, IRIS focuses on the fusion of clinical text, biomedical literature, medical images, and biological data to support tasks such as disease prediction, clinical decision support, public health analytics, biomedical knowledge discovery, and precision healthcare.
IRIS fosters a highly collaborative research culture, bringing together faculty members, researchers, doctoral scholars, and students to address complex real-world problems at the intersection of AI, language, and data. The lab actively promotes open research practices, high-quality publications, open-source contributions, and technology transfer through national and international collaborations with academia, industry, and government agencies.
Developing neural ranking models, semantic query expansion, and web-scale indexing for high-precision document search.
Learn moreCreating robust translation, summarization, and sentiment mining frameworks for low-resource languages.
Learn moreFusing clinical text, biological networks, and medical images to generate comprehensive report summaries.
Learn moreApplying deep learning to genomic sequencing, protein structure folding, and digital drug discovery.
Learn moreTracking sentiment trends, network influence patterns, and detecting misinformation and fake news propagation.
Learn moreIdentifying and resolving algorithmic bias in ranking models to ensure transparent and explainable AI systems.
Learn moreDeveloping neural ranking models, semantic query expansion, and web-scale indexing for high-precision document search.
Learn moreCreating robust translation, summarization, and sentiment mining frameworks for low-resource languages.
Learn moreFusing clinical text, biological networks, and medical images to generate comprehensive report summaries.
Learn moreApplying deep learning to genomic sequencing, protein structure folding, and digital drug discovery.
Learn moreTracking sentiment trends, network influence patterns, and detecting misinformation and fake news propagation.
Learn moreIdentifying and resolving algorithmic bias in ranking models to ensure transparent and explainable AI systems.
Learn moreDiscover our latest papers, books, and conference presentations