Gabriel Loaiza-Ganem
14 papers · 2019–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (29) π Interdisciplinary Bridge Β· Bronze π Keyword Champion (2)
π
Triple Crown
π§¬
Topic Evolution
ποΈ
Keyword Collector
(68)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Deep Learning
(11)
Machine Learning
(11)
Models
(9)
Core Methods
(7)
Artificial Intelligence
(4)
Application Areas
(3)
Bayesian & Probabilistic Β· Artificial Intelligence
(3)
Learning Types
(3)
Optimization & Theory
(3)
Reinforcement Learning
(2)
Applications
(2)
Architectures
(2)
Methods
(2)
Computer Vision
(1)
Bayesian & Probabilistic Β· Machine Learning
(1)
Keywords
generative model
(3)
intrinsic dimension
(3)
variational inference
(3)
diffusion model
(2)
image generation
(2)
latent space
(2)
manifold hypothesis
(2)
normalizing flow
(2)
reparameterization trick
(2)
variational autoencoder
(2)
sample complexity
(1)
embedding learning
(1)
density estimation
(1)
conditional generation
(1)
offline reinforcement learning
(1)
reinforcement learning
(1)
feature extraction
(1)
bayesian nonparametrics
(1)
gaussian process
(1)
maximum likelihood
(1)
Papers
A Geometric Framework for Understanding Memorization in Generative Models
ICLR 2025
A Geometric Explanation of the Likelihood OOD Detection Paradox
ICML 2024
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
NeurIPS 2024
Data-Efficient Multimodal Fusion on a Single GPU
CVPR 2024
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
NeurIPS 2023
TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation
ICML 2023
Verifying the Union of Manifolds Hypothesis for Image Data
ICLR 2023
Bayesian Nonparametrics for Offline Skill Discovery
ICML 2022
C-Learning: Horizon-Aware Cumulative Accessibility Estimation
ICLR 2021
Rectangular Flows for Manifold Learning
NeurIPS 2021
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
NeurIPS 2020
The continuous categorical: a novel simplex-valued exponential family
ICML 2020
Deep Random Splines for Point Process Intensity Estimation of Neural Population Data
NeurIPS 2019
The continuous Bernoulli: fixing a pervasive error in variational autoencoders
NeurIPS 2019