Related papers: A Unified Architecture for N-Dimensional Visualiza…
We develop a pipeline to streamline neural architecture codesign for physics applications to reduce the need for ML expertise when designing models for novel tasks. Our method employs neural architecture search and network compression in a…
Differentiable simulation of soft bodies is a foundation for system identification, trajectory optimization, and Real2Sim transfer. Yet, existing methods such as the differentiable Projective Dynamics (DiffPD) struggle when faced with…
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this…
This report provides an architecture-led analysis of two modern vision-language models (VLMs), Qwen2.5-VL-7B-Instruct and Llama-4-Scout-17B-16E-Instruct, and explains how their architectural properties map to a practical video-to-artifact…
We present a new method for performing Boolean operations on volumes represented as triangle meshes. In contrast to existing methods which treat meshes as 3D polyhedra and try to partition the faces at their exact intersection curves, we…
The freeform architectural modeling process often involves two important stages: concept design and digital modeling. In the first stage, architects usually sketch the overall 3D shape and the panel layout on a physical or digital paper…
Volumetric models have become a popular representation for 3D scenes in recent years. One of the breakthroughs leading to their popularity was KinectFusion, where the focus is on 3D reconstruction using RGB-D sensors. However, monocular…
Abstract data has no natural scale and so interactive data visualizations must provide techniques to allow the user to choose their viewpoint and scale. Such techniques are well established in desktop visualization tools. The two most…
Computationally weak systems and demanding graphical applications are still mostly dependent on linear blendshapes for facial animations. The accompanying artifacts such as self-intersections, loss of volume, or missing soft tissue…
Autonomous exploration of unknown environments is a key capability for mobile robots, but it is largely unsolved for robots equipped with only a single monocular camera and no dense range sensors. In this paper, we present a novel approach…
Navigating complex indoor environments requires a deep understanding of the space the robotic agent is acting into to correctly inform the navigation process of the agent towards the goal location. In recent learning-based navigation…
Accurate 6D object pose estimation is a fundamental capability for embodied agents, yet remains highly challenging in open-world environments. Many existing methods often rely on closed-set assumptions or geometry-agnostic regression…
Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images…
Compute-mode rendering is becoming more and more attractive for non-standard rendering applications, due to the high flexibility of compute-mode execution. These newly designed pipelines often include streaming vertex and geometry…
High-level synthesis, source-to-source compilers, and various Design Space Exploration techniques for pragma insertion have significantly improved the Quality of Results of generated designs. These tools offer benefits such as reduced…
Computing the exact optimal experimental design has been a longstanding challenge in various scientific fields. This problem, when formulated using a specific information function, becomes a mixed-integer nonlinear programming (MINLP)…
Heavy communication, in particular, collective operations, can become a critical performance bottleneck in scaling the training of billion-parameter neural networks to large-scale parallel systems. This paper introduces a four-dimensional…
Shape Expressions (ShEx) are used in various fields of knowledge to define RDF graph structures. ShEx visualizations enable all kinds of users to better comprehend the underlying schemas and perceive its properties. Nevertheless, the only…
Multidimensional scaling is a statistical process that aims to embed high dimensional data into a lower-dimensional space; this process is often used for the purpose of data visualisation. Common multidimensional scaling algorithms tend to…
I begin with a brief history of N-body simulation and visualization and then go on to describe various methods for creating images and animations of modern simulations in cosmology and galactic dynamics. These techniques are incorporated…