Related papers: Shape Inference and Grammar Induction for Example-…

The ability to learn new visual concepts from limited examples is a hallmark of human cognition. While traditional category learning models represent each example as an unstructured feature vector, compositional concept learning is thought…

We propose a computational modeling framework for inducing combinatory categorial grammars from arbitrary behavioral data. This framework provides the analyst fine-grained control over the assumptions that the induced grammar should conform…

Room geometry inference (RGI) aims at estimating room shapes from measured room impulse responses (RIRs) and has received lots of attention for its importance in environment-aware audio rendering and virtual acoustic representation of a…

The prediction of molecular properties is a crucial task in the field of material and drug discovery. The potential benefits of using deep learning techniques are reflected in the wealth of recent literature. Still, these techniques are…

Despite rapid advancements in the capabilities of generative models, pretrained text-to-image models still struggle in capturing the semantics conveyed by complex prompts that compound multiple objects and instance-level attributes.…

This work harnesses interpretable machine learning methods to address the challenging inverse design problem of origami-inspired systems. We show that a decision tree-random forest method is particularly suitable for fitting origami…

Generative modelling for shapes is a prerequisite for In-Silico Clinical Trials (ISCTs), which aim to cost-effectively validate medical device interventions using synthetic anatomical shapes, often represented as 3D surface meshes. However,…

Existing generative models for 3D shapes are typically trained on a large 3D dataset, often of a specific object category. In this paper, we investigate the deep generative model that learns from only a single reference 3D shape.…

Text infilling is defined as a task for filling in the missing part of a sentence or paragraph, which is suitable for many real-world natural language generation scenarios. However, given a well-trained sequential generative model,…

We propose a system for surface completion and inpainting of 3D shapes using generative models, learnt on local patches. Our method uses a novel encoding of height map based local patches parameterized using 3D mesh quadrangulation of the…

In this paper we investigate the problem of inducing a distribution over three-dimensional structures given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called "projective generative adversarial…

Human perception of 3D shapes goes beyond reconstructing them as a set of points or a composition of geometric primitives: we also effortlessly understand higher-level shape structure such as the repetition and reflective symmetry of object…

Recent work has shown the ability to learn generative models for 3D shapes from only unstructured 2D images. However, training such models requires differentiating through the rasterization step of the rendering process, therefore past work…

Crafting a rich and unique environment is crucial for fictional world-building, but can be difficult to achieve since illustrating a world from scratch requires time and significant skill. We investigate the use of recent multi-modal image…

Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word…

We present Probabilistic Structure Integration (PSI), a system for learning richly controllable and flexibly promptable world models from data. PSI consists of a three-step cycle. The first step, Probabilistic prediction, involves building…

Procedural content generation (PCG) is a growing field, with numerous applications in the video game industry and great potential to help create better games at a fraction of the cost of manual creation. However, much of the work in PCG is…

Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these…

Recent progress in deep learning and natural language processing has given rise to powerful models that are primarily trained on a cloze-like task and show some evidence of having access to substantial linguistic information, including some…

This paper presents a method for generating floor plans for structures in Minecraft (Mojang 2009). Given a 3D space, it will auto-generate a building to fill that space using a combination of constrained growth and cellular automata. The…