News

• 1 paper accepted to ICML 2022. 1 paper accepted to ECCV 2022.

• 2 papers accepted to CVPR 2022. 1 paper accepted to ICCS 2022.

• We release a tensor learning library for PyTorch users (TensorLy-Torch). Check out the website to learn how this can help with your deep learning models. [website] [github]

Research Interests

• Recurrent Neural Network (RNN), Muiti-Dimensional LSTM

• Multi-Dimensional Sequence Learning, Spatio-Temporal Learning

• Predictive Learning, Few-shot Learning, Lifelong Learning

Selected Projects

• J Su, W Byeon, F Huang, “Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework”, ICML, 2022

• B Wu*, O Hennigh, J Kautz, S Choudhry, W Byeon*, “Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations”, ICCS 2022 (*) equal contributions
  • Presented at NeurIPS’21 Workshop on ML and the Physical Science
• J Su*, W Byeon*, F Huang, J Kautz, A Anandkumar, “Convolutional Tensor-Train LSTM for Spatio-temporal Learning”, NeurIPS 2020 (*) equal contributions
  • Presented at ECCV’20 Tutorial on Accelerating Computer Vision with Mixed Precision.

• W Byeon, Q Wang, R K Srivastava, P Koumoutsakos, “ContextVP: Fully Context-Aware Video Prediction”, ECCV 2018 (oral)

• PR Vlachas, W Byeon, ZY Wan, TP Sapsis, P Koumoutsakos, “Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks”, Proceedings of the Royal Society A: Mathematical, Physical & Engineering Sciences. 2018