Learning computationally efficient static word and sentence representations

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.

Automatic speech recognition (ASR) systems are well known to perform poorly on dysarthric speech. Previous works have addressed this by speaking rate modification to reduce the mismatch with typical speech. Unfortunately, these approaches rely on transcrib ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition (ASR) on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are train ...

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

To retrieve Surface Solar Radiation (SSR) from satellite images, a baseline reflectance of the observed ground in clear-sky conditions, also called background reflectance, is necessary to distinguish atmospheric absorption and scattering effects from surfa ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Estimating ecosystem-atmosphere fluxes such as evapotranspiration (ET) in a robust manner and at a global scale remains a challenge. Methods based on machine learning (ML) have shown promising results in achieving such upscaling, providing a complementary ...

Intelligent Tutoring Systems (ITS) enhance personalized learning by predicting student answers to provide immediate and customized instruction. However, recent research has primarily focused on the correctness of the answer rather than the student's perfor ...

Monitoring of cardiac output (CO) is a mainstay of hemodynamic management in the acutely or critically ill patient. Invasive determination of CO using thermodilution, albeit regarded as the gold standard, is cumbersome and bears risks inherent to catheteri ...

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

Faithful human performance capture and free-view rendering from sparse RGB observations is a long-standing problem in Vision and Graphics. The main challenges are the lack of observations and the inherent ambiguities of the setting, e.g. occlusions and dep ...

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

Developing agents that can reliably act on our behalf is central to artificial intelligence (AI). These agents must seamlessly interact with tools, like search engines and databases, and collaborate. In this thesis, we study the abstractions, methods, and ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high ...

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

Sonic Human-Robot Interaction aims at equipping robots with the ability to convey emotions and intentions via sounds. Such sounds are typically handcrafted by human experts, which results in expensive, small sound sets with limited expressivity. To overcom ...

Accurate forecasting of photovoltaic (PV) power production is crucial for the integration of more renewable energy sources into the power grid. PV power production is highly intermittent, due to the stochastic cloud behaviour and cloud dynamics. Previous w ...

This paper introduces a novel architecture for Quantum Graph Neural Networks, which is significantly different from previous approaches found in the literature. The proposed approach produces similar outcomes with respect to previous models but with fewer ...

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 ...

Learning computationally efficient static word and sentence representations

Chat with Graph Search

Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models

Social-Transmotion: Promptable Human Trajectory Prediction

Retrieval of Surface Solar Radiation through Implicit Albedo Recovery from Temporal Context

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

On the added value of sequential deep learning for the upscaling of evapotranspiration

Student Answer Forecasting: Transformer-Driven Answer Choice Prediction for Language Learning

Machine learning-enabled estimation of cardiac output from peripheral waveforms is independent of blood pressure measurement location in an in silico population

Driving and suppressing the human language network using large language models

MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

Collaborative AI Agents in the Era of Large Language Models

The multimodality cell segmentation challenge: toward universal solutions

Enhancing skin lesion classification: a CNN approach with human baseline comparison

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life

Automated Generation of Emotion-Conveying Sounds for Robots

Network time series forecasting in photovoltaics power production

A Study on Quantum Graph Neural Networks Applied to Molecular Physics

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance