On Linear Interpolation in the Latent Space of Deep Generative Models

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

We study quantifiers and interpolation properties in ortho- logic, a non-distributive weakening of classical logic that is sound for formula validity with respect to classical logic, yet has a quadratic-time decision procedure. We present a sequent-based p ...

Statistical (machine-learning, ML) models are more and more often used in computational chemistry as a substitute to more expensive ab initio and parametrizable methods. While the ML algorithms are capable of learning physical laws implicitly from data, ad ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

This article investigates the performance and accuracy of continuous Real-Time Kinematic (RTK) Global Navigation Satellite System (GNSS) position tracking for hydromorphological surveys, based on a comprehensive river restoration monitoring campaign. The a ...

This paper investigates the potential impact of deep generative models on the work of creative professionals. We argue that current generative modeling tools lack critical features that would make them useful creativity support tools, and introduce our own ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

In this thesis, we concentrate on advancing high-level behavioral control policies for robotic systems within the framework of Dynamical Systems (DS). Throughout the course of this research, a unifying thread weaving through diverse fields emerges, and tha ...

Traditional example-based learning methods are often limited by static, expert-created content. Hence, they face challenges in scalability, engagement, and effectiveness, as some learners might struggle to relate to the examples or find them relevant. To a ...

The goal of this thesis is the development and the analysis of numerical methods for problems where the unknown is a curve on a smooth manifold. In particular, the thesis is structured around the three following problems: homotopy continuation, curve inter ...

This paper presents a theoretical analysis of linear interpolation as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss lan ...

The accurate, robust and efficient transfer of the deformation gradient tensor between meshes of different resolution is crucial in cardiac electromechanics simulations. This paper presents a novel method that combines rescaled localized Radial Basis Funct ...

This data set provides a computer-assisted proof for the kernel inequalities needed to prove universal optimality in the paper "Universal optimality of the E_8 and Leech lattices and interpolation formulas" (by Cohn, Kumar, Miller, Radchenko, and Viazovska ...

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...

Detailed chemical abundances of very metal-poor (VMP; [Fe/H] < -2) stars are important for better understanding the first stars, early star formation, and chemical enrichment of galaxies. Big on-going and coming high-resolution spectroscopic surveys provid ...

Touchscreens are nowadays the preferred choice for user interfaces in consumer electronics. Significant technological advances have been made in terms of touch sensing and visual quality. However, the haptic feedback offered by commercial products is still ...

Reduced-order models are indispensable for multi-query or real-time problems. However, there are still many challenges to constructing efficient ROMs for time-dependent parametrized problems. Using a linear reduced space is inefficient for time-dependent n ...

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised le ...

MRI is a non-invasive medical imaging modality that is sensitive to patient motion, which constitutes a major limitation in most clinical applications. Solutions may arise from the reduction of acquisition times or from motion-correction techniques, either ...

Fourier transforms are an often necessary component in many computational tasks, and can be computed efficiently through the fast Fourier transform (FFT) algorithm. However, many applications involve an underlying continuous signal, and a more natural choi ...

Federated Learning by nature is susceptible to low-quality, corrupted, or even malicious data that can severely degrade the quality of the learned model. Traditional techniques for data valuation cannot be applied as the data is never revealed. We present ...

On Linear Interpolation in the Latent Space of Deep Generative Models

Chattez avec Graph Search

Interpolation and Quantifiers in Ortholattices

Encoding quantum-chemical knowledge into machine-learning models of complex molecular properties

Extensions of Peer Prediction Incentive Mechanisms

Performance and accuracy of cross‐section tracking methods for hydromorphological habitat assessment in wadable rivers with sparse canopy conditions

Fashioning Creative Expertise with Generative AI: Graphical Interfaces for GAN-Based Design Space Exploration Better Support Ideation Than Text Prompts for Diffusion Models

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Geometric Learning: Leveraging differential geometry for learning and control

GELEX: Generative AI-Hybrid System for Example-Based Learning

Retraction-based numerical methods for continuation, interpolation and time integration on manifolds

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Preserving the positivity of the deformation gradient determinant in intergrid interpolation by combining RBFs and SVD: Application to cardiac electromechanics

Computer-assisted proof of kernel inequalities

Benign Overfitting in Deep Neural Networks under Lazy Training

Analysis of accretion disc structure and stability using open code for vertical structure

Deep Learning for Localized-Haptic Feedback in Tactile Surfaces

Non-intrusive data-driven reduced-order modeling for time-dependent parametrized problems

A structured prediction approach for robot imitation learning

Choreography Controlled (ChoCo) brain MRI artifact generation for labeled motion-corrupted datasets

pyFFS: A Python Library for Fast Fourier Series Computation and Interpolation with GPU Acceleration

A Practical Influence Approximation for Privacy-Preserving Data Filtering in Federated Learning