Kenneth Ge

Kenneth Ge, JooYoung Seo

For blind and low-vision (BLV) individuals, digital math communication is uniquely difficult due to the lack of accessible tools. Currently, the state of the art is either code-based, like LaTeX, or WYSIWYG, like visual editors. However, both paradigms view math communication as primarily a visual typesetting problem, and may be accessible but difficult to use. In this paper, we present an equation editor that is built from the ground up with BLV accessibility in mind. Specifically, we notice that two of the biggest barriers with current technology are the high cognitive load and the lack of spatial relationships. Thus, we build an editor that uses spatial audio cues, muscle memory, tones, and more intuitive navigation to properly contextualize math equations. We discuss how this new paradigm can enable new levels of math communication, engagement, and literacy. Finally, we discuss natural next steps.

Kenneth Ge, Jinglin Li, Shikhar Ahuja

Floaters, cobweb-like shadows that move around a person's visual field, impair vision for nearly 33% of the population, yet have limited treatment options. Floaters especially harm screen use, since they reduce contrast, introduce clutter, and add moving distractions. While existing high-contrast tools offer some help, few address the motion that makes screen use with floaters uniquely difficult. In this paper, we build a floater simulation inspired by the physics of the eye, use it to quantitatively assess text readability at varying levels of motion, and build a novel web extension that minimizes eye movement, maximizing the signal-to-noise ratio of performing browser tasks. Importantly, our tool works not only for text, but for all UI elements, requiring no modifications to existing websites.

Miao Li, Phuc Nguyen, Christopher Tam et al.

Tabular data dominates data science but poses challenges for generative models, especially when the data is limited or sensitive. We present a novel approach to generating synthetic tabular data based on the principle of maximum entropy -- MaxEnt -- called GEM-T, for ``generative entropy maximization for tables.'' GEM-T directly captures nth-order interactions -- pairwise, third-order, etc. -- among columns of training data. In extensive testing, GEM-T matches or exceeds deep neural network approaches previously regarded as state-of-the-art in 23 of 34 publicly available datasets representing diverse subject domains (68\%). Notably, GEM-T involves orders-of-magnitude fewer trainable parameters, demonstrating that much of the information in real-world data resides in low-dimensional, potentially human-interpretable correlations, provided that the input data is appropriately transformed first. Furthermore, MaxEnt better handles heterogeneous data types (continuous vs. discrete vs. categorical), lack of local structure, and other features of tabular data. GEM-T represents a promising direction for light-weight high-performance generative models for structured data.