XMAI at ACL'23
Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning
General GPT
WIP: Multimodal Large Language Model
About Me
Deep Learning Engineer
Currently, I work as a Deep Learning Engineer after graduating from Georgia Tech with a Masters in Computer Science, with a focus in Machine/Deep Learning. At Georgia Tech, I was a member of the CLAWS research group where I collaborated with Gaurav Verma and was advised by Professor Srijan Kumar. At CLAWS, my research contributions revolved around the robustness of multimodal and NLP models/sytems [Paper].
Prior to that, I completed my Bachelors in Computer Science at the University of Virginia. During my undergrad I was a student researcher for Professor Hongning Wang, where I studied deep learning models based recommendation systems. Specifically, the issues of popularity bias and manners in which one can evaluate and debias such models [Paper].
Current Research Interests: Multimodal Learning and Large Language Models
I work among other researchers at LAION on open-source AI projects, hoping to advance the science while allowing its capabilities to be used and impact a larger array of people. Right now,
I am working towards creating a large multimodal model with the ability to understand and reason with interleaved multimodal inputs (such as Flamingo), while also being able to produce outputs in a number of modalities.
In my free time I enjoy playing sports/video games, reading papers, working out, and learning new things.
🌹💐
