Related papers: Neuro-Visualizer: An Auto-encoder-based Loss Lands…

Neural network parameterizations exhibit inherent symmetries that yield multiple equivalent minima within the loss landscape. Scale Graph Metanetworks (ScaleGMNs) explicitly leverage these symmetries by proposing an architecture equivariant…

Contemporary deep learning architectures lack principled means for capturing and handling fundamental visual concepts, like objects, shapes, geometric transforms, and other higher-level structures. We propose a neurosymbolic architecture…

Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we…

Given a single RGB image of a complex outdoor road scene in the perspective view, we address the novel problem of estimating an occlusion-reasoned semantic scene layout in the top-view. This challenging problem not only requires an accurate…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Artificial Intelligence & Nanotechnology are promising areas for the future of humanity. While Deep Learning based Computer Vision has found applications in many fields from medicine to automotive, its application in nanotechnology can open…

Training large neural networks (NNs) requires optimizing high-dimensional data-dependent loss functions. The optimization landscape of these functions is often highly complex and textured, even fractal-like, with many spurious local minima,…

In recent years many methods have been developed to understand the internal workings of neural networks, often by describing the function of individual neurons in the model. However, these methods typically only focus on explaining the very…

Finding collective variables to describe some important coarse-grained information on physical systems, in particular metastable states, remains a key issue in molecular dynamics. Recently, machine learning techniques have been intensively…

Delineation of curvilinear structures is an important problem in Computer Vision with multiple practical applications. With the advent of Deep Learning, many current approaches on automatic delineation have focused on finding more powerful…

We propose a methodology for lidar super-resolution with ground vehicles driving on roadways, which relies completely on a driving simulator to enhance, via deep learning, the apparent resolution of a physical lidar. To increase the…

Model reduction of high-dimensional dynamical systems alleviates computational burdens faced in various tasks from design optimization to model predictive control. One popular model reduction approach is based on projecting the governing…

Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes. In this work, we present Wild Visual Navigation (WVN), an…

Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries, which is crucial for embodied AI applications such as autonomous navigation, robotics, and augmented reality. Learning 3D language…

This paper describes a new neuroimaging analysis toolbox that allows for the modeling of nonlinear effects at the voxel level, overcoming limitations of methods based on linear models like the GLM. We illustrate its features using a…

Deep learning has shown significant potential in diagnosing neurodegenerative diseases from MRI data. However, most existing methods rely heavily on large volumes of labeled data and often yield representations that lack interpretability.…

Building accurate maps is a key building block to enable reliable localization, planning, and navigation of autonomous vehicles. We propose a novel approach for building accurate maps of dynamic environments utilizing a sequence of LiDAR…

Quantification of the stationary points and the associated basins of attraction of neural network loss surfaces is an important step towards a better understanding of neural network loss surfaces at large. This work proposes a novel method…

Geo-localization from a single image at planet scale (essentially an advanced or extreme version of the kidnapped robot problem) is a fundamental and challenging task in applications such as navigation, autonomous driving and disaster…

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been…