Related papers: UnrealVis: A Testing Laboratory of Optimization Te…

Dimensionality Reduction (DR) techniques such as t-SNE and UMAP are popular for transforming complex datasets into simpler visual representations. However, while effective in uncovering general dataset patterns, these methods may introduce…

For over half a century, the computer mouse has been the primary tool for interacting with digital data, yet it remains a limiting factor in exploring complex, multi-scale scientific images. Traditional 2D visualization methods hinder…

While deep neural networks (DNNs) are an increasingly popular way to query large corpora of data, their significant runtime remains an active area of research. As a result, researchers have proposed systems and optimizations to reduce these…

We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize…

Developers are usually unaware of the impact of code changes to the performance of software systems. Although developers can analyze the performance of a system by executing, for instance, a performance test to compare the performance of…

Simulating physical systems is a core component of scientific computing, encompassing a wide range of physical domains and applications. Recently, there has been a surge in data-driven methods to complement traditional numerical simulations…

Many graphics rendering algorithms used in both real-time games and virtual reality applications can get performance boosts by temporally reusing previous computations. However, algorithms based on temporal reuse are typically measured…

Data visualization should be accessible for all analysts with data, not just the few with technical expertise. Visualization recommender systems aim to lower the barrier to exploring basic visualizations by automatically generating results…

Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging task. To remedy this unsatisfactory situation, a number of…

Unsupervised machine learning is widely used to mine large, unlabeled datasets to make data-driven discoveries in critical domains such as climate science, biomedicine, astronomy, chemistry, and more. However, despite its widespread…

VFIVE is a scientific visualization application for CAVE-type immersive virtual reality systems. The source codes are freely available. VFIVE is used as a research tool in various VR systems. It also lays the groundwork for developments of…

This study advances real-time volumetric cloud rendering in Computer Graphics (CG) by developing a specialized shader in Unreal Engine (UE), focusing on realistic cloud modeling and lighting. By leveraging ray-casting-based lighting…

Data visualization is the process by which data of any size or dimensionality is processed to produce an understandable set of data in a lower dimensionality, allowing it to be manipulated and understood more easily by people. The goal of…

Nonlinear programming targets nonlinear optimization with constraints, which is a generic yet complex methodology involving humans for problem modeling and algorithms for problem solving. We address the particularly hard challenge of…

The virtual reality (VR) provides us a three-dimensional, immersive, and fully interactive visualization environment. To make the best use of the VR's potential in scientific visualization, a VR visualization software named VFIVE has been…

Natural Language Explanations (NLE) aim at supplementing the prediction of a model with human-friendly natural text. Existing NLE approaches involve training separate models for each downstream task. In this work, we propose Uni-NLX, a…

Multilayer relationships among entities and information about entities must be accompanied by the means to analyze, visualize, and obtain insights from such data. We present open-source software (muxViz) that contains a collection of…

Visual navigation is essential for robotics and embodied AI. However, existing foundation models, particularly those with transformer decoders, suffer from high computational overhead and lack interpretability, limiting their deployment in…

Achieving a desirable balance between rendering quality and real-time performance is a long-standing challenge in modern game and rendering engines, particularly on resource-constrained mobile devices such as laptops, tablets, and…

The reasoning capabilities of Large Language Models (LLMs) have increased greatly over the last few years, as have their size and complexity. Nonetheless, the use of LLMs in production remains challenging due to their unpredictable nature…