Related papers: Position: Assistive Agents Need Accessibility Alig…
My research centers on the development of context-adaptive AI systems to improve end-user adoption through the integration of technical methods. I deploy these AI systems across various interaction modalities, including user interfaces and…
Agentic AI represents a significant shift in how intelligence is applied within organizations, moving beyond AI-assisted tools toward autonomous systems capable of reasoning, decision-making, and coordinated action across workflows. As…
Assistive devices are a key aspect in wearable systems for biomedical applications, as they represent potential aids for people with physical and sensory disabilities that might lead to improvements in the quality of life. This chapter…
Video production workflows offer a rich and demanding arena for evaluating multimodal AI agents: they require composite capabilities across text, image, audio, and video understanding, along with long-horizon planning, and tool use. To this…
Over the past decade, considerable research has been directed towards assistive technologies to support people with vision impairments using machine learning, computer vision, image enhancement, and/or augmented/virtual reality. However,…
The adaptation of teaching slides to instructors' situated teaching needs, including pedagogical styles and their students' context, is a critical yet time-consuming task for educators. Through a series of educator interviews, we first…
In mixed-ability collaboration, eye contact is often treated as a default cue for attention and turn-taking. As these signals are primarily visual, they are not reliably accessible to people with visual impairments. While prior work…
As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of performing multiple tasks simultaneously. However,…
While AI is often introduced into organizations to drive innovation and efficiency, many adoption efforts fail as workers resist and struggle to integrate these systems. These failures point to a deeper issue: workers, the very people…
In recent decades, several assistive technologies have been developed to improve the ability of blind and visually impaired (BVI) individuals to navigate independently and safely. At the same time, simultaneous localization and mapping…
Agentic visual analytics (VA) represents an emerging class of systems in which large language model (LLM)-driven agents autonomously plan, execute, evaluate, and iterate across the full visual analytics pipeline. By shifting users from…
Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive systems and acquiring the vast interaction data needed for training adaptive agents. This paper…
As AI adoption expands across human society, the problem of aligning AI models to match human preferences remains a grand challenge. Currently, the AI alignment field is deeply divided between behavioral and representational approaches,…
Agentic AI seeks to endow systems with sustained autonomy, reasoning, and interaction capabilities. To realize this vision, its assumptions about agency must be complemented by explicit models of cognition, cooperation, and governance. This…
People with vision impairments (VIPs) often rely on their remaining vision when interacting with user interfaces. Simulating visual impairments is an effective tool for designers, fostering awareness of the challenges faced by VIPs. While…
Continuous physiological monitoring is central to emergency care, yet deploying trustworthy AI is challenging. While LLMs can translate complex physiological signals into clinical narratives, it is unclear how agentic systems perform…
Visually impaired people face significant challenges when attempting to interact with and understand complex environments, and traditional assistive technologies often struggle to quickly provide necessary contextual understanding and…
We are in a transformative era, and advances in Artificial Intelligence (AI), especially the foundational models, are constantly in the news. AI has been an integral part of many applications that rely on automation for service delivery,…
Modern AI enables a high-level, declarative form of interaction: Users describe the intended outcome they wish an AI to produce, but do not actually create the outcome themselves. In contrast, in traditional user interfaces, users invoke…
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…