An Optimal Control Perspective on Diffusion-Based Generative Modeling
Explore optimal control theory's connection to diffusion-based generative modeling. Gain insights into stochastic differential equations, Hamilton-Jacobi-Bellman equations, and novel sampling methods for unnormalized densities.
Transport, Variational Inference and Diffusions
Explore connections between optimal transport and variational inference, focusing on stochastic differential equations and Girsanov transformations. Discover novel sampling and generative modeling techniques.
Action Matching: Learning Stochastic Dynamics from Samples
Explore Action Matching for learning stochastic dynamics from samples. Discover applications in quantum systems, biology, and generative modeling. Gain insights into novel approaches for simulating trajectories.
Deep Generative Modeling
Explore deep generative modeling, including autoencoders, VAEs, and GANs. Learn about latent variables, representation learning, and applications in debiasing and image synthesis.
Divide (or Convolve) and Conquer: Data Comparison with Wiener Filters
Explore Wiener filters for data comparison in machine learning, enhancing image reconstruction and translation robustness in various applications like compression and generative modeling.
Planning with Diffusion for Flexible Behavior Synthesis
Learn flexible behavior synthesis using diffusion models for planning, exploring compositional trajectories, goal-directed planning, and offline reinforcement learning techniques.
On Robustness and Generative Modeling
Explore adversarial training's impact on AI robustness and generative modeling. Gain insights into energy dynamics, robust overfitting, and the connection between robust classifiers and generative capabilities.
Learning with Limited Supervision - Generative Modeling Approaches
Explore generative modeling approaches for learning with limited labeled data. Discover techniques leveraging prior knowledge for weak supervision in machine learning tasks.
Deep Learning Advances in Uncertainty and Generative Modeling - Session 1
Explore cutting-edge deep learning research, including Bayesian methods, generative modeling, visual concept programming, conformal regression, and heteroskedastic regression analysis.