IIIT-H researchers secure 10 ANRF Advanced Research Grants from 15,700 proposals nationwide
HYDERABAD: Ten research projects from the International Institute of Information Technology, Hyderabad (IIIT-H) have been selected for the Advanced Research Grant (ARG) of the Anusandhan National Research Foundation (ANRF), emerging as winners among nearly 15,700 proposals submitted nationwide.
The ARG is the flagship funding programme of ANRF, the Government of India’s national body for research and innovation. It supports ambitious, investigator-driven projects led by established researchers working on high-impact scientific ideas.
The selected proposals from IIIT-H span fields ranging from quantum computing and robotics to speech technology, artificial intelligence and climate science, highlighting the breadth of the institute’s research ecosystem.
Quantum computing reliability and secure communications research
One of the selected projects, led by Lalitha Vadlamani, focuses on quantum error correction through a study titled “Quantum LDPC Codes and Topological Codes for Fault-Tolerant Quantum Computation”.
Quantum bits, or qubits, are extremely fragile and prone to errors, making reliable computation difficult. “These are very, very fragile objects,” Vadlamani said, adding that error correction is essential because “even to just hold the qubits for some time… in a stable way would be nearly impossible.”
Her research aims to design coding techniques that protect quantum information from errors, a key step toward building scalable quantum computers. The field has seen global breakthroughs in recent years, including work implemented by companies such as Google.
Another project led by Atul Singh Arora, with collaborators Uttam Singh and Venkata Koppula from IIT Delhi, explores how classical computers can verify the output of remote quantum devices. The project, titled “Classical Control of Untrusted Quantum Devices,” seeks to create protocols that allow users to confirm whether a quantum computer has performed computations correctly.
In digital communications research, Arti Yardi and Prasad Krishnan are studying “Blind Identification of Channel Codes”. Their work addresses how receivers can decode signals even when the encoding scheme is unknown a problem relevant in secure communications and intelligence applications.
Robotics, speech technology and multilingual AI
In robotics, Girish Varma and Antony Thomas are developing a system that enables robots to judge whether a physical action is feasible before attempting it. Their project, “Learned Estimation of Action Plausibility (LEAP)”, uses machine learning to help robots quickly determine whether tasks such as grasping objects are possible in cluttered environments.
Preliminary tests show the method is up to 44 times faster than conventional robotic planning systems while maintaining more than 91% accuracy.
In speech technology, Chiranjeevi Yarra, along with Parameswari Krishnamurthy and Rajakrishnan, is working on making AI-generated speech more natural by modelling prosody the rhythm, pitch and tone of spoken language. The project focuses on Indian languages such as Hindi, Bengali, Telugu, Tamil and Malayalam.
“Typically when we speak, our speaking style is natural, but machines are not so natural,” Yarra said.
Anil Kumar Vuppula’s research focuses on improving automatic speech recognition (ASR) for India’s multilingual environment. His project aims to develop domain-aware systems capable of recognising trilingual speech Hindi, English and Telugu in real-world settings such as hospitals and classrooms.
Accessibility technologies and climate research
Vineet Gandhi’s project, “IndiG Multimodal”, aims to develop speech accessibility tools for Indian languages. His lab has already created systems in English that convert slurred speech into clear speech, transform whispers into normal voice, and generate speech from lip movements or throat vibrations.
“This will be an app for people who can’t speak or struggle to speak. They can communicate in that and the other person will hear a cleaner version of their speech,” Gandhi said.
Another accessibility-focused project involves a collaboration between Ashutosh Modi of IIT Kanpur and C V Jawahar of IIIT-H. The researchers aim to build one of the largest datasets for Indian Sign Language (ISL), potentially exceeding one million aligned video, text and audio samples. The project also plans to develop AI-based systems capable of translating between sign language and text or speech.
Rainfall prediction and AI-driven drug discovery
In climate science, Shruti Upadhyaya of IIT Hyderabad and Kuldeep Kurte of IIIT-H are studying rainfall patterns across India through a project that combines satellite data, ground observations and artificial intelligence.
The research will evaluate satellite rainfall products against rain gauge data and develop machine learning models to reduce estimation errors. The improved datasets could help forecast extreme events such as flash floods more accurately.
Meanwhile, Deva Priyakumar and Vinod P K are working on AI-driven drug discovery for aggressive cancers. Their project seeks to design molecules that inhibit EphA2, a protein linked to several tumour types but currently lacking approved targeted therapies.
By combining AI-based screening with physics-based simulations and laboratory testing, the researchers aim to produce promising pre-clinical drug candidates and develop new computational frameworks for precision cancer therapies.
