Doctoral Student Research in Natural Language Processing & Computer Vision
Department researchers work at the intersection of Computer Vision, Natural Language Processing, and Artificial Intelligence, building computational models that can reason. Computer Vision is about connecting the contents of an image, which is pixels, with words that humans can understand and use for an application. In the Computer Vision domain, our researchers work on Generative AI, trying to synthesize images that look realistic and follow physical properties that are plausible.
Natural Language Processing is to enable machines to understand and speak human language. Research focuses on explaining and evaluating models’ capabilities and inner workings, as well as identifying potential risks and vulnerabilities. Our ultimate goal is to develop comprehensible, controllable, and trustworthy intelligence systems.
Faculty
Faculty members leading research in NLP & CV are as follows:
The work below represent current student research projects.
|
Improved Visual Grounding through Self-Consistent Explanations Presenter: Catherine He
|
Grounding Language Models for Visual Entity Recognition Presenter: Zilin Xiao |
|
ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders Presenter: Jefferson Hernandez |
|
PropTest: Automatic Property Testing for Improved Visual Programming Presenter: Jaywon Koo
|
|
Language Models are Solomonoff Learners in Arithmetic Presenter: Chunyuan Deng
|
|
SAFR: Neuron Redistribution for Interpretability Presenter: Ruidi Chang
|