Description: Personal Webpage
I am a Reasearch Scientist at Meta AI working on Human-Centric Multimodal Machine Learning and Generative Modeling. Prior to that I completed my PhD at the Language Technologies Institute at Carnegie Mellon University where I was advised by Dr. Louis-Philippe Morency (LP) in the Multicomp Lab . My research focused on endowing agents and remote avatars with Social Intelligence by means of Multimodal Learning . One of the use-cases where we extensively apply these technologies is Computer Animation . These di
Co-speech gestures are a key channel of human communication, making them important for personalized chat agents to generate. In the past, gesture generation models assumed that data for each speaker is available all at once, and in large amounts. However in practical scenarios, speaker data comes sequentially and in small amounts as the agent personalizes with more speakers, akin to a continual learning paradigm. While more recent works have shown progress in adapting to low-resource data, they catastrophic
Lecture slide presentations, a sequence of pages that contain text and figures accompanied by speech, are constructed and presented carefully in order to optimally transfer knowledge to students. Previous studies in multimedia and psychology attribute the effectiveness of lecture presentations to their multimodal nature. As a step toward developing AI to aid in student learning as intelligent teacher assistants, we introduce the Multimodal Lecture Presentations dataset as a large-scale benchmark testing the