Research &
Explore our contributions to the field of AI research through academic papers, conference presentations, and technical reports
Filter by Year
Filter by Topic
ViViD - Vision Language model for Unified Visual Understanding of Documents
Adithya S Kolavi
CVPR 2025 | Emergent Visual Abilities and Limits of Foundation Models (EVAL-FoMo 2025)
A vision-language model specifically optimized for document understanding tasks, capable of processing diverse document formats with high accuracy.
Nayana OCR: A Scalable Framework for Document OCR in Low-Resource Languages
Adithya S Kolavi, Samarth P, Vyoman Jain
NAACL 2025 | Language Models for Underserved Communities
Development of a specialized OCR system designed for low-resource Indic languages, addressing unique challenges in character recognition and document processing.
Nayana - A Unified Foundation Model for Multilingual, Multimodal, and Multitask Intelligence
Adithya S Kolavi, Samarth P, Vyoman Jain
LlamaCon 2025 | LLama Impact Grant 2024 winner
Winner of the 2024 Llama impact grant from Meta, this paper presents a foundation model architecture designed for multilingual and multimodal applications.
CAPTAIN: Continuous Automated Planning Through Autonomous Internet Navigation
Adithya S Kolavi
AAAI 2025 | Large Language Models for Planning (LM4Plan)
A novel framework for autonomous web navigation and task planning using large language models to perform complex multi-step operations.
Opportunities
Join our team or support our research
Join our Team
Application Process
Please fill out the form below to show interest in our open positions. We will review your application and get back to you within 2-3 weeks.
Support Our Research
If you like our research and would like to sponsor our projects and open source initiatives, please get in touch. Your sponsorship will greatly help us continue developing innovative solutions and advancing the field of AI.
- ✓Support cutting-edge AI research
- ✓Contribute to open source development
- ✓Help make AI accessible to everyone
