Taejong Joo

According to our database, Taejong Joo authored at least 8 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2025

Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context.

Taejong Joo, Diego Klabjan

CoRR, February, 2025

2024

Improving self-training under distribution shifts via anchored confidence with theoretical guarantees.

Taejong Joo, Diego Klabjan

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation.

Taejong Joo, Diego Klabjan

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2020

Deep Learning Requires Explicit Regularization for Reliable Predictive Probability.

Taejong Joo, Uijung Chung

CoRR, 2020

Being Bayesian about Categorical Probability.

Taejong Joo, Uijung Chung, Min-Gwan Seo

Proceedings of the 37th International Conference on Machine Learning, 2020

Regularizing activations in neural networks via distribution matching with the Wasserstein metric.

Taejong Joo, Donggu Kang, Byunghoon Kim

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Formalizing Human-Machine Interactions for Adaptive Automation in Smart Manufacturing.

Taejong Joo, Dongmin Shin

IEEE Trans. Hum. Mach. Syst., 2019

An adaptive approach for determining batch sizes using the hidden Markov model.

Taejong Joo, Minji Seo, Dongmin Shin

J. Intell. Manuf., 2019