Leading groundbreaking research in multimodal foundation models, like my work on Llama 3/4, DinoV2, Chameleon, MetaCLIP and MaVIL among others. Graduate School in Multimodal Machine Learning at Carnegie Mellon University (Dept. Rank #1), and Undergrad from IIT Kanpur in Computer Science and Engineering (JEE rank 165, GPA 9.9/10) passionate about pushing the boundaries of AI.
I'm an Applied Research Scientist Lead at Meta AI, where I spearhead the development of multimodal foundation models including Chameleon, Llama 3/4, DinoV2 etc. My work spans trillion token scale pretraining, mixture of expert architectures, and next generation conversational AI agents.
With a Masters from Carnegie Mellon (Department Rank #1) and experience across Meta, Amazon Alexa, and Citadel, I bridge cutting-edge research with real-world applications.
A focused journey through leading tech institutions, specializing in multimodal foundation models, large-scale AI infrastructure, and quantitative research.
Spearheading multimodal foundation model development. Instrumental in creating Llama 3/4 and Chameleon models. Conducting pioneering research in trillion-token pretraining and advanced conversational AI agents.
Developed comprehensive visual-language navigation benchmarks. Engineered efficient multimodal transformers and optimized video processing applications for Alexa's core AI systems.
Architected automated ML pipelines for high-frequency trading strategies. Optimized distributed computing frameworks to handle large-scale financial data processing.
Advancing the frontiers of AI and machine learning through impactful research contributions
A breakthrough self-supervised learning approach that learns powerful visual representations without requiring labeled data, achieving state-of-the-art performance across multiple computer vision tasks.
Novel multi-modal learning framework that jointly processes audio and video through masked reconstruction, enabling robust cross-modal understanding.
Pioneering foundation model architecture that seamlessly integrates multiple modalities through early fusion, enabling unified reasoning across text, images, and code.
Innovative approach to creating mixture-of-experts models by combining specialized language models, achieving superior performance with efficient parameter utilization.
Comprehensive analysis of CLIP training data, providing crucial insights into data quality, bias, and their impact on model performance and fairness.
Thorough evaluation framework for vision-language models, revealing important limitations and proposing improvements for better multi-modal understanding.
Interested in collaborating on cutting-edge AI research? Looking for expertise in multimodal foundation models or large-scale AI systems? I'm always excited to discuss innovative projects and research opportunities.