Detection of Settlements in Tanzania and Mozambique by Many Regional Few-Shot Models

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.

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 ...

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 ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ...

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 ...

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and accelerators tailored for t ...

Patterns in nature arise from processes interacting across a continuum of spatial scales, where new relationships emerge at each level of investigation. These patterns are nested features encompassing fine-scale local patterns, such as topography and geolo ...

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 ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Metal-organic frameworks (MOFs) are a class of crystalline porous materials that exhibit a vast chemical space owing to their tunable molecular building blocks with diverse topologies. An unlimited number of MOFs can, in principle, be synthesized. Machine ...

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in co ...

Abstractive summarization has seen big improvements in recent years, mostly due to advances in neural language modeling, language model pretraining, and scaling models and datasets. While large language models generate summaries that are fluent, coherent, ...

Models trained with counterfactually augmented data learn representations of the causal structure of tasks, enabling robust generalization. However, high-quality counterfactual data is scarce for most tasks and not easily generated at scale. When crowdsour ...

Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress them to smaller net ...

Vision-Language Pre-training (VLP) has advanced the performance of many visionlanguage tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous w ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

Author summaryIn recent years, the application of deep learning represented a breakthrough in the mass spectrometry (MS) field by improving the assignment of the correct sequence of amino acids from observable MS spectra without prior knowledge, also known ...

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

Robustness of medical image classification models is limited by its exposure to the candidate disease classes. Generalized zero shot learning (GZSL) aims at correctly predicting seen and unseen classes and most current GZSL approaches have focused on the s ...

Detection of Settlements in Tanzania and Mozambique by Many Regional Few-Shot Models

Chat with Graph Search

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

The multimodality cell segmentation challenge: toward universal solutions

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Augmenting large language models with chemistry tools

Social-Transmotion: Promptable Human Trajectory Prediction

Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures

At what spatial scale does natural selection operate? Using multiscale frameworks to calibrate the effects of environmental factors across landscape continuums

Sparse autoregressive neural networks for classical spin systems

Improving Generalization of Pretrained Language Models

A multi-modal pre-training transformer for universal transfer learning in metal-organic frameworks

4M: Massively Multimodal Masked Modeling

Interpretable Representation Learning and Evaluation for Abstractive Summarization

DISCO: Distilling Counterfactuals with Large Language Models

Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Transformer Models for Vision

Multienzyme deep learning models improve peptide de novo sequencing by mass spectrometry proteomics

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

Modeling Structured Data in Attention-based Models

Class Specific Feature Disentanglement and Text Embeddings for Multi-label Generalized Zero Shot CXR Classification