News and Events

Upcoming Events

Talk title: And the AIR-1 in GATE goes to…
Speaker: Chandra Sekhar Seelamantula, Professor, Department of Electrical Engineering, Indian Institute of Science
Date: 19 August 2026
Time: 4 PM
Venue: 102, Seminar hall, Department of Computational and Data Sciences, IISc/online*
Registration link: https://forms.cloud.microsoft/r/njD8KY6DBb

*the Teams Meet link will be sent to the registered email ID

Talk abstract:

Large language models (LLMs) have demonstrated remarkable performance on a wide range of standardised examinations, yet their capabilities on engineering-oriented, multimodal reasoning tasks remain underexplored. In this talk, we introduce GATEBench, a benchmark based on the Graduate Aptitude Test in Engineering (GATE), to evaluate the scientific reasoning, mathematical problem-solving, and visual understanding capabilities of state-of-the-art LLMs. This is the first-of-its-kind effort in the context of the GATE exam.

We assess seven frontier models across six GATE 2025 and 2026 test papers comprising computer science, data science and artificial intelligence, electrical engineering, electronics and communication engineering, and mathematics. Our evaluation compares the model performance with the official All India Rank-1 (AIR-1) scores and analyses the performance across subjects, question types (multiple choice questions, multiple select questions, and numerical answer type), and image-based versus text-based questions.

Beyond simply asking whether AI can top the GATE exam, the study offers an opportunity to examine what kinds of reasoning tasks remain challenging for current AI systems, and what this tells us about the evolving capabilities of AI. The talk will discuss these findings and their broader implications for AI, education, and possibly the future of engineering examinations. The findings also set the goalpost for the next-generation AI systems in the context of engineering and scientific reasoning tasks.

This is work done in collaboration with Parth Gupte, Department of EE, IISc.

Speaker biography:

Chandra Sekhar Seelamantula is a Professor in the Department of Electrical Engineering at the Indian Institute of Science. He received his Bachelor of Engineering degree with Prof K K Nair Gold Medal from Osmania University in 1999 and PhD from IISc (Electrical Communication Engineering) in 2005.

After completing postdoctoral research at EPFL, Switzerland (2006–2009), he joined IISc as a faculty member in 2009 and now leads the Spectrum Lab. His research interests include signal processing, machine learning, generative AI, computational imaging, and AI for healthcare diagnostics.

He has served in various editorial roles including Senior Area Editor for IEEE Signal Processing Letters and IEEE Transactions on Image Processing. He received Prof Priti Shankar Teaching Award (2013) from IISc, Digital Health Prize (2018) at National Bio-Entrepreneurship Competition, Outstanding Editorial Board Member award from IEEE Transactions on Image Processing in 2023, prestigious research grants, and is a co-recipient of several Qualcomm Innovation Fellowships together with PhD students. He served as the Chair of GATE–JAM office, IISc during 2022–2024 and was the Organising Chair of GATE 2024.

Past Events