no code implementations • 6 Nov 2023 • Ehsan Pajouheshgar, Yitao Xu, Alexander Mordvintsev, Eyvind Niklasson, Tong Zhang, Sabine Süsstrunk
We propose Mesh Neural Cellular Automata (MeshNCA), a method for directly synthesizing dynamic textures on 3D meshes without requiring any UV maps.
no code implementations • 11 Sep 2023 • Johannes von Oswald, Eyvind Niklasson, Maximilian Schlegel, Seijin Kobayashi, Nicolas Zucchet, Nino Scherrer, Nolan Miller, Mark Sandler, Blaise Agüera y Arcas, Max Vladymyrov, Razvan Pascanu, João Sacramento
Transformers have become the dominant model in deep learning, but the reason for their superior performance is poorly understood.
no code implementations • 6 Feb 2023 • Alexander Mordvintsev, Ettore Randazzo, Eyvind Niklasson
We present a differentiable formulation of abstract chemical reaction networks (CRNs) that can be trained to solve a variety of computational tasks.
1 code implementation • 15 Dec 2022 • Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo, João Sacramento, Alexander Mordvintsev, Andrey Zhmoginov, Max Vladymyrov
We start by providing a simple weight construction that shows the equivalence of data transformations induced by 1) a single linear self-attention layer and by 2) gradient-descent (GD) on a regression loss.
3 code implementations • 26 Nov 2021 • Alexander Mordvintsev, Eyvind Niklasson
We study the problem of example-based procedural texture synthesis using highly compact models.
no code implementations • 22 Jun 2021 • Alexander Mordvintsev, Ettore Randazzo, Eyvind Niklasson
Reaction-Diffusion (RD) systems provide a computational framework that governs many pattern formation processes in nature.
3 code implementations • 15 May 2021 • Alexander Mordvintsev, Eyvind Niklasson, Ettore Randazzo
Neural Cellular Automata (NCA) have shown a remarkable ability to learn the required rules to "grow" images, classify morphologies, segment images, as well as to do general computation such as path-finding.
2 code implementations • 2 Jul 2020 • Ettore Randazzo, Eyvind Niklasson, Alexander Mordvintsev
We present a novel method for learning the weights of an artificial neural network - a Message Passing Learning Protocol (MPLP).
1 code implementation • 21 Oct 2019 • Valts Blukis, Yannick Terme, Eyvind Niklasson, Ross A. Knepper, Yoav Artzi
Learning uses both simulation and real environments without requiring autonomous flight in the physical environment during training, and combines supervised learning for predicting positions to visit and reinforcement learning for continuous control.
5 code implementations • EMNLP 2018 • Dipendra Misra, Andrew Bennett, Valts Blukis, Eyvind Niklasson, Max Shatkhin, Yoav Artzi
We propose to decompose instruction execution to goal prediction and action generation.