136 citations · 213 across the 6 of their papers we have counts for
7 papers
A Family of LLMs Liberated from Static Vocabularies
Aleph Alpha, :, Adnen Abdessaied +35
Tokenization is a central component of natural language processing in current large language models (LLMs), enabling models to convert raw text into processable units. Although lea…
Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
Martin Simonovsky
A graph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines and there is a na…
GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
Martin Simonovsky, Nikos Komodakis
Deep learning on graphs has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks, which is in contrast with…
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
Loic Landrieu, Martin Simonovsky
We propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points. We argue that the organization…
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
Martin Simonovsky, Nikos Komodakis
A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avo…
A Deep Metric for Multimodal Registration
Martin Simonovsky, Benjamín Gutiérrez-Becker, Diana Mateus +2
Multimodal registration is a challenging problem in medical imaging due the high variability of tissue appearance under different imaging modalities. The crucial component here is…
OnionNet: Sharing Features in Cascaded Deep Classifiers
Martin Simonovsky, Nikos Komodakis
The focus of our work is speeding up evaluation of deep neural networks in retrieval scenarios, where conventional architectures may spend too much time on negative examples. We pr…