Talk Slides
- Discrete Generative Modeling with Masked Diffusions
- Designing Sequence Models with Wavelets and Multiresolution Convolutions
- Stein’s Method for Modern Machine Learning: From Gradient Estimation to Generative Modeling
- Spectral Methods and Generative Modeling: A Unifying Perspective
- Differentiable Programming in Probabilistic Models
- Sampling with Mirrored Stein Operators
- Neural Networks as Inter-Domain Inducing Points
- Function-Space Orthogonality in Probabilistic Learning
- Sparse Orthogonal Variational Inference for Gaussian Processes
- Inference Networks for Gaussian Processes
- A Spectral Approach to Gradient Estimation for Implicit Distributions