The Escalator Problem: Identifying Implicit Motion Blindness in AI for Accessibility
This addresses a trust and safety issue for the blind and visually impaired community, but it is a position paper with no new method or data, making it incremental in impact.
The paper identifies a critical failure mode in Multimodal Large Language Models (MLLMs) for assistive technologies, termed the Escalator Problem, where models cannot perceive an escalator's direction of travel due to Implicit Motion Blindness, stemming from frame-sampling in video understanding.
Multimodal Large Language Models (MLLMs) hold immense promise as assistive technologies for the blind and visually impaired (BVI) community. However, we identify a critical failure mode that undermines their trustworthiness in real-world applications. We introduce the Escalator Problem -- the inability of state-of-the-art models to perceive an escalator's direction of travel -- as a canonical example of a deeper limitation we term Implicit Motion Blindness. This blindness stems from the dominant frame-sampling paradigm in video understanding, which, by treating videos as discrete sequences of static images, fundamentally struggles to perceive continuous, low-signal motion. As a position paper, our contribution is not a new model but rather to: (I) formally articulate this blind spot, (II) analyze its implications for user trust, and (III) issue a call to action. We advocate for a paradigm shift from purely semantic recognition towards robust physical perception and urge the development of new, human-centered benchmarks that prioritize safety, reliability, and the genuine needs of users in dynamic environments.