I'm a Senior Research Scientist at NVIDIA, NYC. My research focuses primarily on natural language processing (NLP). Some of the key topics which drive my research are:

• Long-context models: How should models efficiently process long-text documents? What should be the structure of the working memory? How to pretrain LMs to encourage the modeling of the latent long-context dependencies? [1][2][3]
• State Tracking with Language Models: Understanding text requires that the models are building an implicit/explit representation of the underlying world. Are language models trained on mere surface form capable of representing the underlying world? [1][2]