SPOC: Imitating <i>Shortest Paths</i> in Simulation Enables Effective Navigation and Manipulation in the Real World

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.

The rapid evolution of Machine Learning (ML) workloads, particularly Deep Neural Networks (DNNs) and Transformer-based models, has intensified demands on computing architectures, highlighting the limitations of traditional von Neumann systems due to the me ...

In real-world speech data processing, the scarcity of annotated data and the abundance of unlabelled speech data present a significant challenge. To address this, we propose an efficient data selection pipeline for fine-tuning ASR models by generating pseu ...

Context. Nonideal magnetohydrodynamic (MHD) effects are thought to be a crucial component of the star formation process. Numerically, several complications render the study of nonideal MHD effects in 3D simulations extremely challenging and hinder efforts ...

The nematode Caenorhabditis elegans offers a uniquely tractable model for studying the relationships between neuronal activity, connectivity, and behavior. Despite its simplicity, key questions remain about how information flows through its nervous system ...

We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probab ...

While classical in many theoretical settings-and in particular in statistical physics-inspired works-the assumption of Gaussian i.i.d. input data is often perceived as a strong limitation in the context of statistics and machine learning. In this study, we ...

Numerical simulations have become one of the key tools used by theorists in all the fields of astrophysics and cosmology. The development of modern tools that target the largest existing computing systems and exploit state-of-the-art numerical methods and ...

An adaptive moving mesh finite difference scheme is developed for tokamak magneto-hydrodynamic (MHD) simulations, based on the CLT code (S. Wang and Z.W. Ma, Phys. Plasmas, 2015). Our numerical scheme is built on the MHD equations in curvilinear coordinate ...

Intelligent Fault Diagnosis (IFD) based on deep learning has proven to be an effective and flexible solution, attracting extensive research. Deep neural networks can learn rich representations from vast amounts of representative labeled data for various ap ...

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the pe ...

The evolution of electronics has largely relied on downscaling to meet the continuous needs for faster and highly integrated devices(1). As the channel length is reduced, however, classic electronic devices face fundamental issues that hinder exploiting ma ...

With the growing awareness about ipRGC-influenced light (IIL) responses, design applications related to these responses are flourishing. To compare design options and optimize lighting conditions for building occupants, lighting simulations are typically u ...

With the onset of large-scale astronomical surveys capturing millions of images, there is an increasing need to develop fast and accurate deconvolution algorithms that generalize well to different images. A powerful and accessible deconvolution method woul ...

Loop closure detection helps simultaneous localization and mapping systems reduce map and state uncertainty via recognizing previously visited places along the path of a mobile robot. However, visual loop closure detection is susceptible to scenes with dyn ...

SPOC: Imitating <i>Shortest Paths</i> in Simulation Enables Effective Navigation and Manipulation in the Real World

Chattez avec Graph Search

Stop Wasting your Cache! Bringing Machine Learning into Cache Computing

Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering

A fast and robust recipe for modeling nonideal magnetohydrodynamic effects in star formation simulations

Behaviorally Relevant Information Content in Interneuron Activity

Global Group Fairness in Federated Learning via Function Tracking

Gaussian universality of perceptrons with random labels

Swift : a modern highly parallel gravity and smoothed particle hydrodynamics solver for astrophysical and cosmological applications

An adaptive moving mesh finite difference scheme for tokamak magneto-hydrodynamic simulations

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Electronic metadevices for terahertz applications

Validation of spectral simulation tools in the context of ipRGC-influenced light responses of building occupants

Deep learning-based galaxy image deconvolution

PlaceNet: A multi-scale semantic-aware model for visual loop closure detection