{"ID":2883752,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07989","arxiv_id":"2508.07989","title":"The Escalator Problem: Identifying Implicit Motion Blindness in AI for Accessibility","abstract":"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.","short_abstract":"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-...","url_abs":"https://arxiv.org/abs/2508.07989","url_pdf":"https://arxiv.org/pdf/2508.07989v1","authors":"[\"Xiantao Zhang\"]","published":"2025-08-11T13:53:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}