Jinyung Hong

13 papers A 1C 1Journal 9Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Debiasing Global Workspace: A Cognitive Neural Framework for Learning Debiased and Interpretable Representations. UniReps Jinyung Hong, Eun Som Jeon, Changhoon Kim, Keun Hee Park, Utkarsh Nath, Yezhou Yang, Pavan K. Turaga, Theodore P. Pavlic
2024	J	`jnl`	Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings. CoRR Jinyung Hong, Yearim Kim, Keun Hee Park, Sangyu Han, Nojun Kwak, Theodore P. Pavlic
2024	A	`conf`	Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace. WACV Jinyung Hong, Keun Hee Park, Theodore P. Pavlic
2024	J	`jnl`	Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks. CoRR Jinyung Hong, Eun Som Jeon, Changhoon Kim, Keun Hee Park, Utkarsh Nath, Yezhou Yang, Pavan K. Turaga, Theodore P. Pavlic
2024	J	`jnl`	Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks. CoRR Jinyung Hong, Theodore P. Pavlic
2023	J	`jnl`	Concept-Centric Transformers: Concept Transformers with Object-Centric Concept Learning for Interpretability. CoRR Jinyung Hong, Theodore P. Pavlic
2023	—	`conf`	Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks. UniReps Jinyung Hong, Theodore P. Pavlic
2022	J	`jnl`	Learning to modulate random weights can induce task-specific contexts for economical meta and continual learning. CoRR Jinyung Hong, Theodore P. Pavlic
2021	C	`conf`	An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning. NeSy Jinyung Hong, Theodore P. Pavlic
2021	J	`jnl`	An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning. CoRR Jinyung Hong, Theodore P. Pavlic
2021	J	`jnl`	KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks. CoRR Jinyung Hong, Theodore P. Pavlic
2021	J	`jnl`	Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection. CoRR Jinyung Hong, Theodore P. Pavlic
2020	J	`jnl`	Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness. CoRR Jinyung Hong, Theodore P. Pavlic