Predoctoral Researcher in the Vision Language and Learning Group led by Dr. Anand Mishra at the Indian Institute of Technology Jodhpur. My research focuses on multimodal deep learning, particularly vision-language models and data-centric approaches for low-resource and culturally significant domains.
Current work includes developing dialogue-driven diagnostic models in collaboration with AIIMS and applying computer vision techniques to restore degraded ancient Indian manuscripts at IGNCA.
- Portfolio: katikapalli.github.io
- Google Scholar: scholar.google.com
- LinkedIn: linkedin.com/in/katikapallilokesh