Jinyung Hong
Hello, I'm Jinyung Hong, a Ph.D. candidate in computer science at Arizona State University.
I belong to the SEADS lab, supervised by Dr. Theodore P. Pavlic.
My research aims to apply principles and techniques from neuroscience, biology, and cognitive science to implement new interpretable Intelligence that can collaborate with humans and help them make decisions. To this end, I conduct research that spans the areas of neuro-symbolic computing, continual learning, and interpretable AIs, which are crucial components to building human-like AI systems with cognitive abilities.
Research Interests: Bio-inspired Computing, Neuro-symbolic Computing, Continual Learning, Model Interpretability.
News
Spring 2024: Received an ASU School of Computing and Augmented Intelligence (SCAI) Doctoral Fellowship. ๐
Nov 28, 2023: Received an ASU Graduate and Professional Student Association (GPSA) Travel Grant Award. ๐
Nov 20, 2023: Received the Best UniReps Proceeding Paper Award. ๐
Recent Publications
Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
arXiv.org (2024)
Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024
Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
UniReps: Unifying Representations in Neural Models Workshop @ NeurIPS 2023
Selected the Best UniReps Proceeding Paper