1.3k citations · 3.8k across the 19 of their papers we have counts for
14 papers · 1 filter
The Coupling Within: Flow Matching via Distilled Normalizing Flows
David Berthelot, Tianrong Chen, Jiatao Gu +6
Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration ste…
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
Vimal Thilak, Chen Huang, Omid Saremi +5
Joint embedding (JE) architectures have emerged as a promising avenue for acquiring transferable data representations. A key obstacle to using JE methods, however, is the inherent…
Adaptivity and Modularity for Efficient Generalization Over Task Complexity
Samira Abnar, Omid Saremi, Laurent Dinh +8
Can transformers generalize efficiently on problems that require dealing with examples with different levels of difficulty? We introduce a new task tailored to assess generalizatio…
Generative Modeling with Phase Stochastic Bridges
Tianrong Chen, Jiatao Gu, Laurent Dinh +3
Diffusion models (DMs) represent state-of-the-art generative models for continuous inputs. DMs work by constructing a Stochastic Differential Equation (SDE) in the input space (ie,…
Perfect density models cannot guarantee anomaly detection
Charline Le Lan, Laurent Dinh
Thanks to the tractability of their likelihood, several deep generative models show promise for seemingly straightforward but important applications like anomaly detection, uncerta…
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
Chin-Wei Huang, Laurent Dinh, Aaron Courville
In this work, we propose a new family of generative flows on an augmented data space, with an aim to improve expressivity without drastically increasing the computational cost of s…
Discrete Flows: Invertible Generative Models of Discrete Data
Dustin Tran, Keyon Vafa, Kumar Krishna Agrawal +2
While normalizing flows have led to significant advances in modeling high-dimensional continuous distributions, their applicability to discrete distributions remains unknown. In th…
A RAD approach to deep mixture models
Laurent Dinh, Jascha Sohl-Dickstein, Hugo Larochelle +1
Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities…
Learnable Explicit Density for Continuous Latent Space and Variational Inference
Chin-Wei Huang, Ahmed Touati, Laurent Dinh +4
In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the…
Sharp Minima Can Generalize For Deep Nets
Laurent Dinh, Razvan Pascanu, Samy Bengio +1
Despite their overwhelming capacity to overfit, deep learning architectures tend to generalize relatively well to unseen data, allowing them to be deployed in practice. However, ex…
Density estimation using Real NVP
Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference…
A Recurrent Latent Variable Model for Sequential Data
Junyoung Chung, Kyle Kastner, Laurent Dinh +3
In this paper, we explore the inclusion of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining elements of the variational autoen…
NICE: Non-linear Independent Components Estimation
Laurent Dinh, David Krueger, Yoshua Bengio
We propose a deep learning framework for modeling complex high-dimensional densities called Non-linear Independent Component Estimation (NICE). It is based on the idea that a good…
Predicting Parameters in Deep Learning
Misha Denil, Babak Shakibi, Laurent Dinh +2
We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accur…