At the recently concluded TechForward series seminar on AI in Vehicles, Prof. C V Jawahar described the mobility-related research efforts being undertaken at IIITH. Here’s a summarized version. At IIITH, we have been aiming to solve problems on Indian roads and driving conditions using data-driven technologies. With the help of techniques from machine learning, computer vision, computer graphics, computational sensing, and allied areas, we have been creating solutions and transferring these solutions across diverse practical conditions on roads. One of the research studies that was undertaken includes early anticipation of driver actions before the onset of a manoeuvre, such as a turn, a lane change, a sudden halt and so on. When you know the driver in front of you is going to take a right turn without indicating with a signal, you anticipate and get ready for it perhaps by slowing down or changing lanes.

In an interview with Business World team, Prof. P J Narayanan describes the industrial, social and healthcare applications of the translational research being carried out at the institute. Answering a question, Prof. P J Narayanan says, IIITH has been a leader in AI and related areas through KCIS that was endowed by TCS in 2015. Our strengths include all core Al areas including machine learning, cognitive science, data analytics, natural language processing, speech processing and synthesis, robotics, computer vision, etc. Building on the foundations of academic research, we have been focusing on applied and translational research in the past several years. This involves research with specific industrial or social application as the focus. We established two entities – INAI and RCTS – for large-scale applied research. The Technology Innovation Hub established by the DST at the institute has data-driven applications as its focus and works synergistically with the institute’s research centres and labs.

A team from IIITH has introduced Patram-7B-Instruct, India’s first vision-language foundational model designed specifically for complex document understanding. This landmark achievement is part of the BharatGen initiative, a government-supported program to develop India-centric Multimodal Large Language Models, funded by the Department of Science and Technology (DST). Patram-7B-Instruct is a 7-billion parameter AI model trained on a large, diverse corpus of Indian documents. It can analyze scanned or photographed documents and respond accurately to natural language instructions, making it a versatile tool for varied applications across sectors. Despite its relatively compact size, Patram surpasses larger international models such as DeepSeek-VL-2 on prominent benchmarks like DocVQA and VisualMRC.