675 citations · 1.8k across the 55 of their papers we have counts for
57 papers
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
Hierarchical VAE with a Diffusion-based VampPrior
Anna Kuzina, Jakub M. Tomczak
Deep hierarchical variational autoencoders (VAEs) are powerful latent variable generative models. In this paper, we introduce Hierarchical VAE with Diffusion-based Variational Mixt…
Generative AI Systems: A Systems-based Perspective on Generative AI
Jakub M. Tomczak
Large Language Models (LLMs) have revolutionized AI systems by enabling communication with machines using natural language. Recent developments in Generative AI (GenAI) like Vision…
Variational Stochastic Gradient Descent for Deep Neural Networks
Haotian Chen, Anna Kuzina, Babak Esmaeili +1
Current state-of-the-art optimizers are adaptive gradient-based optimization methods such as Adam. Recently, there has been an increasing interest in formulating gradient-based opt…
Mixed Models with Multiple Instance Learning
Jan P. Engelmann, Alessandro Palma, Jakub M. Tomczak +2
Predicting patient features from single-cell data can help identify cellular states implicated in health and disease. Linear models and average cell type expressions are typically…
De Novo Drug Design with Joint Transformers
Adam Izdebski, Ewelina Weglarz-Tomczak, Ewa Szczurek +1
De novo drug design requires simultaneously generating novel molecules outside of training data and predicting their target properties, making it a hard task for generative models.…
A comparison of controller architectures and learning mechanisms for arbitrary robot morphologies
Jie Luo, Jakub Tomczak, Karine Miras +1
The main question this paper addresses is: What combination of a robot controller and a learning method should be used, if the morphology of the learning robot is not known in adva…
Lamarck's Revenge: Inheritance of Learned Traits Can Make Robot Evolution Better
Jie Luo, Karine Miras, Jakub Tomczak +1
Evolutionary robot systems offer two principal advantages: an advanced way of developing robots through evolutionary optimization and a special research platform to conduct what-if…
Exploring Continual Learning of Diffusion Models
Michał Zając, Kamil Deja, Anna Kuzina +4
Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data. However, tra…
Discouraging posterior collapse in hierarchical Variational Autoencoders using context
Anna Kuzina, Jakub M. Tomczak
Hierarchical Variational Autoencoders (VAEs) are among the most popular likelihood-based generative models. There is a consensus that the top-down hierarchical VAEs allow effective…
Learning Data Representations with Joint Diffusion Models
Kamil Deja, Tomasz Trzcinski, Jakub M. Tomczak
Joint machine learning models that allow synthesizing and classifying data often offer uneven performance between those tasks or are unstable to train. In this work, we depart from…
Modelling Long Range Dependencies in D: From Task-Specific to a General Purpose CNN
David M. Knigge, David W. Romero, Albert Gu +5
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In…
A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference
Emile van Krieken, Thiviyan Thanapalasingam, Jakub M. Tomczak +2
We study the problem of combining neural networks with symbolic reasoning. Recently introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as DeepProbLog, perfo…
Towards a General Purpose CNN for Long Range Dependencies in D
David W. Romero, David M. Knigge, Albert Gu +4
The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learn…
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models
Kamil Deja, Anna Kuzina, Tomasz Trzciński +1
Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art performance in generative modeling. Their main strength comes from their unique setup in which a model (the ba…
Alleviating Adversarial Attacks on Variational Autoencoders with MCMC
Anna Kuzina, Max Welling, Jakub M. Tomczak
Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations. Moreover, they could be further used in…
The Effects of Learning in Morphologically Evolving Robot Systems
Jie Luo, Aart Stuurman, Jakub M. Tomczak +2
Simultaneously evolving morphologies (bodies) and controllers (brains) of robots can cause a mismatch between the inherited body and brain in the offspring. To mitigate this proble…
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak +3
When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kern…
Training Deep Spiking Auto-encoders without Bursting or Dying Neurons through Regularization
Justus F. Hübotter, Pablo Lanillos, Jakub M. Tomczak
Spiking neural networks are a promising approach towards next-generation models of the brain in computational neuroscience. Moreover, compared to classic artificial neural networks…
Storchastic: A Framework for General Stochastic Automatic Differentiation
Emile van Krieken, Jakub M. Tomczak, Annette ten Teije
Modelers use automatic differentiation (AD) of computation graphs to implement complex Deep Learning models without defining gradient computations. Stochastic AD extends AD to stoc…
Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks
Anna Kuzina, Max Welling, Jakub M. Tomczak
In this work, we explore adversarial attacks on the Variational Autoencoders (VAE). We show how to modify data point to obtain a prescribed latent code (supervised attack) or just…
Invertible DenseNets with Concatenated LipSwish
Yura Perugachi-Diaz, Jakub M. Tomczak, Sandjai Bhulai
We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient extension of Residual Flows. The method relies on an analysis of the Lipschitz continuity of the co…
CKConv: Continuous Kernel Convolution For Sequential Data
David W. Romero, Anna Kuzina, Erik J. Bekkers +2
Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizo…
General Invertible Transformations for Flow-based Generative Modeling
Jakub M. Tomczak
In this paper, we present a new class of invertible transformations with an application to flow-based generative models. We indicate that many well-known invertible transformations…