Publications
Publications
Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
Hong, Jinyung, Jeon, Eun Som, Kim, Changhoon, Park, Keun Hee, Nath, Utkarsh, Yang, Yezhou, Turaga, Pavan and Pavlic, Theodore P.
arXiv.org (2024)
Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace
Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace
Hong, Jinyung, Park, Keun Hee, and Pavlic, Theodore P.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024
Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
Hong, Jinyung, and Pavlic, Theodore P.
UniReps: Unifying Representations in Neural Models Workshop @ NeurIPS 2023
Selected the Best UniReps Proceeding Paper
Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning
Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning
Hong, Jinyung, and Pavlic, Theodore P.
arXiv.org (2023)
Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
Hong, Jinyung, and Pavlic, Theodore P.
The First International Workshop on Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations (CLeaR) at the AAAI Conference on Artificial Intelligence 2022
An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
Hong, Jinyung, and Pavlic, Theodore P.
Proceedings of the 15th International Workshop on Neuro-Symbolic Learning and Reasoning (NeSy 20/21)
KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks
KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks
Hong, Jinyung, and Pavlic, Theodore P.
arXiv.org (2021)