A phase transition in diffusion models reveals the hierarchical nature of data

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Neural networks have shown to be a powerful tool to represent the ground state of quantum many-body systems, including fermionic systems. However, efficiently integrating lattice symmetries into neural representations remains a significant challenge. In th ...

Advanced wave engineering demands robust, efficient, and new-degree-of-freedom manipulations in wave intrinsic properties like amplitude, phase, polarization, and even spatial structure. To tackle this, this thesis advances photonic wave manipulation by sy ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

When a plasma disrupts in a tokamak, significant heat and electromagnetic loads are deposited onto the surrounding device components. These forces scale with plasma current and magnetic field strength, making disruptions one of the key challenges for futur ...

Machine learning models (e.g., neural networks) achieve high accuracy in wind power forecasting, but they are usually regarded as black boxes that lack interpretability. To address this issue, the paper proposes a glass-box model that combines high accurac ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

Machine learning and artificial intelligence methods have achieved remarkable success, matching and even surpassing human capabilities in various complex tasks. However, many demonstrations have generally neglected a critical part of the intelligence that ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

Understanding how interacting particles approach thermal equilibrium is a major challenge of quantum simulators(1,2). Unlocking the full potential of such systems towards this goal requires flexible initial state preparation, precise time evolution and ext ...

Over the past years, image generation and manipulation have achieved remarkable progress due to the rapid development of generative AI based on deep learning. Recent studies have devoted significant efforts to address the problem of face image manipulation ...

This paper proposes a novel approach to improve the performance of distributed nonlinear control systems while preserving stability by leveraging Deep Neural Networks (DNNs). We build upon the Neural System Level Synthesis (Neur-SLS) framework and introduc ...

A pressure-induced triclinic-to-monoclinic phase transition has been caught 'in the act' over a wider series of high-pressure synchrotron diffraction experiments conducted on a large, photoluminescent organo-gold(I) compound. Here, we describe the mechanis ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

Machine learning has transformed many fields and has recently found applications in chemistry and materials science. The small datasets commonly found in chemistry sparked the development of sophisticated machine learning approaches that incorporate chemic ...

Data-driven techniques are increasingly used to replace electronic-structure calculations of matter. In this context, a relevant question is whether machine learning (ML) should be applied directly to predict the desired properties or combined explicitly w ...

Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that theoretical resul ...

A phase transition in diffusion models reveals the hierarchical nature of data

Chat with Graph Search

Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations

Topological Effects in Wave Scattering and Metamaterials

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Learning to Reason with Neural Networks: Principles and Methods

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Plasma state monitoring and disruption characterization using multimodal VAEs

Explainable modeling for wind power forecasting: A Glass-Box model with high accuracy

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

A comparative analysis of gene expression profiling by statistical and machine learning approaches

Sequential Reasoning with Socially Caused Beliefs

Computational design of complex protein folds and soluble analogs of membrane proteins

Thermalization and criticality on an analogue-digital quantum simulator

Towards the Detection of AI-Synthesized Human Face Images

Optimal distributed control with stability guarantees by training a network of neural closed-loop maps

Structure-property relationship of a complex photoluminescent arylacetylide-gold(I) compound. I: a pressure-induced phase transformation caught in the act

Sparse autoregressive neural networks for classical spin systems

Leveraging large language models for predictive chemistry

Electronic Excited States from Physically Constrained Machine Learning

High-performance deep spiking neural networks with 0.3 spikes per neuron