About Me

Hi, I’m Anirudh, a first-year PhD student at the Indian Institute of Science (IISc). I graduated with a Bachelor of Technology, majoring in Computer Science and Engineering with a minor in Robotics and Artificial Intelligence from the Indian Institute of Technology Guwahati (IIT Guwahati). I am deeply passionate about continual learning for Large Language Models (LLMs), with a focus on how these systems can acquire new knowledge from a changing world and apply it reliably in future interactions.

Previously, I worked at Adobe Research. There, I collaborated with Dr. Apoorv Saxena and Dr. Balaji V. Srinivasan on advancing the attribution engine for Adobe Acrobat AI Assistant, a system that provides document references as evidence for AI-generated answers. Notably, I led the development of the technology powering attribution in contracts, which was highlighted by Adobe’s CEO in a Fox Business interview (6:45–7:15). My broader work focused on improving attribution through multimodality and multilinguality, detecting and mitigating textual/visual hallucinations, optimizing LLM inference, improving context focus in LLMs, and revisualizing infographics for better user consumption. I tend to approach these challenges by leveraging model internals and explainability to ensure transparent and reliable AI systems.

During my undergraduate studies at IIT Guwahati, I completed my bachelor’s thesis under the guidance of Prof. Arijit Sur. My research explored Visual Representation Learning, specifically harnessing inherent intra-class variation to improve contrastive learning methods. This approach provided richer and more effective contrasts compared to traditional data augmentations. Previously, I worked with Prof. Shyamanta M. Hazarika on grasp recognition, employing techniques like Inverse Reinforcement Learning and high-level semantic information such as object affordances.