Workshops Organization:

Conferences, Seminars, and Workshops Presentations:

  • A Primal-Dual Framework for Transformers and Neural Networks. Special Session on "Mathematics of Machine Learning", Canadian Mathematical Society Winter Meeting, 2022. (Invited talk)

  • Transformer with Fourier Integral Attentions. Deep Learning for Sequence Modeling Minisymposium, the SIAM Conference on Computational Science and Engineering (CSE), 2023. (Invited talk)

  • Principled Models for Machine Learning. Math Machine Learning Seminar, the Max Planck Institute for Mathematics in the Sciences and UCLA, Applied Math Colloquium at UCLA, 2022. (Invited talk)

  • Transformer with a Mixture of Gaussian Keys. Geometry of Machine Learning, the 4th Annual Meeting of the SIAM Texas-Louisiana Section, 2021. (Invited talk)

  • Momentum-Based and Fast Multipole Methods for Designing Deep Learning Models. Mathematical Foundation of Deep Learning with the Applications to PDE, the 4th Annual Meeting of the SIAM Texas-Louisiana Section, 2021. (Invited talk)

  • Brain-inspired Robust Vision Using Convolutional Neural Networks with Feedback. NeurIPS NeuroAI Workshop, 2019. (Poster)

  • Conditional Continuous Normalizing Flows for Physics-Inspired Learning. NVIDIA Onsite Research Event, 2019. (Lightning Talk)

  • Neural Rendering Model: Rethinking Neural Networks from the Joint Generation and Prediction Perspective. NeurIPS Workshop on Integration of Deep Learning Theories, 2018. (Contributed talk)

  • EnergyNet: Energy-Efficient Dynamic Inference. NeurIPS Workshop on Compact Deep Neural Network Representation with Industrial Applications, 2018. (Poster)

  • Tremor Generative Adversarial Network (TremorGAN): Deep Generative Model Approach for Geophysical Signal Generation. NeurIPS Workshop on Machine Learning for Geophysical and Geochemical Signals, 2018. (Poster)

  • The Latent-Dependent Deep Rendering Model. ICML Workshop on Theoretical Foundations and Applications of Deep Generative Models, 2018. (Poster)

  • Mixed Reality Generative Adversarial Networks: Closing the Visual Gap between Synthetic and Real Images. Amazon Graduate Research Symposium, 2017. (Poster)

  • A Probabilistic Framework for Deep Learning. Computational and System Neuroscience Conference (COSYNE), 2016. (Poster)