I’m a PhD student at UW-Madison working with Yuhang Zhao studying
human-computer interaction (HCI) in the madAbility Lab.
My primary research interests include human-computer interaction (HCI), extended reality (AR / VR / MR
/ XR), accessibility (a11y), and intelligent systems. My PhD thesis focuses on using computer vision and large language models to make extended reality platforms more accessible to people with disabilities.
My other interests include computer graphics, immersive video (livestreams, 360° cameras,
projection mapping), and how they can be applied to education (including ai-assisted learning (AIAL)), communications (from advertising to foreign
languages), esports, and healthcare.
Before Wisconsin, I earned my BS
in CS from The University of Texas at Austin alongside
certifications in Digital Arts & Media and immersive technologies. There, I worked with Amy Pavel on live video accessibility for screenreader users and Erin Reilly using augmented reality for young adult skin cancer
prevention.
Outside of work, I track all the music I listen to on last.fm. I also enjoy longboarding, cooking, backpacking, watching YouTube videos, language learning, achievement hunting, and moderating online communities.
Daniel Killough, Justin Feng, Rithvik Dyava, ZX Ching, Yapeng Tian, Yuhang Zhao
Using state-of-the-art object detection, zero-shot depth estimation, and multimodal large language models to identify virtual objects in social VR applications for blind and low vision people.
Ruijia Chen*, Daniel Killough*, Leo Cui, Victor Suciu, Bilge Mutlu
Evaluating effects of mixed reality's tendency to drift objects on user perception and performance of task difficulty.
Daniel Killough, Tiger F. Ji, Kexin Zhang, Yaxin Hu, Yu Huang, Ruofei Du, Yuhang Zhao
Analyzing developer challenges on integrating a11y features into their XR apps. Covering a11y features for people with visual, cognitive, motor, and speech & hearing impairments.
Daniel Killough, Amy Pavel
Making live video more accessible to blind users by crowdsourcing audio descriptions
for
real-time playback. Crowdsourced descriptions with 18 sighted community experts and
evaluated
with 9 blind participants.
Ru Wang, Zach Potter, Yun Ho, Daniel Killough, Linda Zeng, Sanbrita Mondal, Yuhang Zhao
System using eyetracking to augment passages of text, supporting low vision peoples'
reading challenges (e.g., line switching and difficult word recognition).