A Connection Between Score Matching and Denoising Autoencoders
Theoretical paper proving the equivalence between training Denoising Autoencoders and performing Score Matching on a …
Generative Models
Notes on VAEs, diffusion models, GANs, and other generative approaches. Covers theory, architectures, and training techniques for generation tasks.
A Convexity Principle for Interacting Gases
Introduces displacement interpolation to prove ground state uniqueness via optimal transport, establishing foundations …
Building Normalizing Flows with Stochastic Interpolants
A continuous-time normalizing flow using stochastic interpolants and quadratic loss to bypass costly ODE …
Flow Matching for Generative Modeling
A simulation-free framework for training Continuous Normalizing Flows using Conditional Flow Matching and Optimal …
Flow Straight and Fast
A unified ODE-based framework for generative modeling and domain transfer that learns straight paths for fast 1-step …
Neural Ordinary Differential Equations
Introduces ODE-Nets, a continuous-depth neural network model parameterized by ODEs, enabling constant memory …
Score-Based Generative Modeling with SDEs
Unified SDE framework for score-based generative models, introducing Predictor-Corrector samplers and achieving SOTA on …
Mixture Density Networks
Seminal 1994 paper introducing MDNs to model arbitrary conditional probability distributions using neural networks.
Auto-Encoding Variational Bayes (VAE Paper Summary)
Summary of Kingma & Welling's foundational VAE paper introducing the reparameterization trick and variational …
IWAE: Importance Weighted Autoencoders
Summary of Burda, Grosse & Salakhutdinov's ICLR 2016 paper introducing Importance Weighted Autoencoders for tighter …
Contrastive Learning for Variational Autoencoder Priors
Aneja et al.'s NeurIPS 2021 paper introducing Noise Contrastive Priors (NCPs) to address VAE's 'prior hole' problem with …