Hi, my name is Raghav Mehta (राघव मेहता in Hindi). I am a graduate student at the Robotics Institute at Carnegie Mellon University.

Previously, I was a Senior Data Scientist - Computer Vision Research at Akridata, working on computer vision research focused on vision-language alignment and mission critical AI systems.

My research interests are multimodal large language models (MLLMs), representation learning, visual anomaly detection, few-shot domain adaptation, synthetic data generation, and building robust, interpretable AI systems for real-world deployment.

I received my bachelor’s degree in Computer Science and Engineering from Jaypee Institute of Information Technology. During my undergraduate studies, I worked on probabilistic modeling and deep learning–based sequence modeling with Prof. Neetu Sardana.