Jaesik Yoon

Hi, I'm Jaesik(재식)! I am a senior machine learning developer in SAP. I am working to explore a variety of new opportunities to extend the generality of Artificial Intelligence (AI) besides developing AI services. Before that, I worked in Samsung electronics and graduated from KAIST.

With Sungjin, we have explored Meta-Learning [c2, c3, c4], Object-Centric Representation (OCR) [c5, p2], Reinforcement Learning [w1, p2].

Please feel free to let me know if you want to discuss or ask anything!

Google Scholar / Github / Email

Publications:

[p2] An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning J. Yoon, Yi-Fu Wu, H. Bae, S. Ahn Preprint Paper

[w1] TransDreamer: Reinforcement Learning with Transformer World Models C. Chen*, Yi-Fu Wu*, J. Yoon*, S. Ahn Deep RL NeurIPS 2021 Paper

[c5] Generative Video Transformer: Can Objects be the Words? Yi-Fu Wu, J. Yoon, S. Ahn ICML 2021 Paper

[c4] Robustifying Sequential Neural Processes J. Yoon, G. Singh, S. Ahn ICML 2020 Paper Code

[c3] Sequential Neural Processes G. Singh*, J. Yoon*, Y. Son, S. Ahn NeurIPS 2019 (Spotlight, 2.4%) Paper Code

[p1] One-Shot Learning for Text-to-SQL Generation D Lee, J Yoon, J Song, S Lee, S Yoon Preprint Paper

[c2] Bayesian Model-Agnostic Meta Learning J. Yoon*, T. Kim*, O. Dia, S. Kim, Y. Bengio, S. Ahn NeurIPS 2018 (Spotlight, 3.5%) Talk Paper Code

[c1] A hierarchical-structured dictionary learning for image classification J Yoon, J Choi, CD Yoo ICIP 2014 (Oral) Paper