Related papers: When Models Manipulate Manifolds: The Geometry of …
Can expressiveness of a drawing be traced with a computer? In this study a neural network (perceptron) and a support vector machine are used to classify line drawings. To do this the line drawings are attributed values according to a…
This paper begins with a description of methods for estimating image probability density functions that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space-not…
Padding tokens are widely used in large language models (LLMs) to equalize sequence lengths during batched inference. While they should be fully masked, implementation errors can cause them to influence computation, and the extent of this…
From the literature, it is demonstrated that performing text-line segmentation directly in the run-length compressed handwritten document images significantly reduces the computational time and memory space. In this paper, we investigate…
Human vision is able to compensate imperfections in sensory inputs from the real world by reasoning based on prior knowledge about the world. Machine learning has had a significant impact on computer vision due to its inherent ability in…
When a reader encounters a word in English, they split the word into smaller orthographic units in the process of recognizing its meaning. For example, "rough", when split according to phonemes, is decomposed as r-ou-gh (not as r-o-ugh or…
Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…
Deep generative models learn the data distribution, which is concentrated on a low-dimensional manifold. The geometric analysis of distribution transformation provides a better understanding of data structure and enables a variety of…
Sketches, with their expressive potential, allow humans to convey the essence of an object through even a rough contour. For the first time, we harness this expressive potential to improve segmentation performance in challenging tasks like…
Modern machine learning increasingly leverages the insight that high-dimensional data often lie near low-dimensional, non-linear manifolds, an idea known as the manifold hypothesis. By explicitly modeling the geometric structure of data…
Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of…
The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is…
Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations. While explicit probing tasks can be used to verify the…
Current controls over diffusion models (e.g., through text or ControlNet) for image generation fall short in recognizing abstract, continuous attributes like illumination direction or non-rigid shape change. In this paper, we present an…
Predictive coding has emerged as an influential normative model of neural computation, with numerous extensions and applications. As such, much effort has been put into mapping PC faithfully onto the cortex, but there are issues that remain…
We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles…
Current text-to-image models struggle to provide precise camera control using natural language alone. In this work, we present a framework for precise camera control with global scene understanding in text-to-image generation by learning…
In this paper we use character variety methods to study homomorphisms between the fundamental groups of 3-manifolds, in particular those induced by non-zero degree maps. A {\it knot manifold} is a compact, connected, irreducible, orientable…
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied…
The paper studies the local geometry of embedding clouds induced by \emph{controlled local classes of semantically close sentences}. The central question is how controlled paraphrase-like semantic variation is organized in sentence…