{
  "abstract": "Multimodal large language models (MLLMs) have expanded artificial intelligence beyond text to include visual and auditory information. However, tactile interaction remains comparatively fragmented across sensing hardware, haptic signal interpretation, tactile generation, and device-specific feedback mechanisms. This paper proposes Smartphone-Native Bidirectional Tactile Multimodal Intelligence (SBTMI), a conceptual framework for integrating tactile input and physical tactile output into smartphone-centered multimodal large language model systems. Unlike approaches that focus exclusively on tactile classification, tactile captioning, or the generation of haptic effects from textual descriptions, the proposed framework organizes tactile perception, semantic reasoning, tactile generation, physical actuation, and feedback-based adaptation within a unified interaction architecture. The framework consists of five principal components: a tactile acquisition interface, a tactile representation module, a multimodal reasoning controller, a tactile generation module, and a device-specific actuation interface. A closed-loop interaction mechanism enables the system to compare intended tactile effects with subsequent sensor observations and adjust its outputs accordingly. The framework distinguishes native smartphone capabilities from capabilities requiring external tactile sensors or actuators. We formulate research questions, define optimization objectives and evaluation metrics, and propose experiments for assessing tactile understanding, generation quality, cross-modal consistency, latency, robustness, and closed-loop performance. This work is a conceptual research proposal rather than an empirically validated system. Its contribution is a unified architectural and experimental framework for investigating bidirectional tactile intelligence in smartphone-centered multimodal AI.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Jincheng Zhang",
      "orcid": "0009-0005-1860-0009"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7vetewxypj63g.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23494137",
  "fulltext_url": null,
  "id": "7vetewxypj63g",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23494137",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23494137/files/Smartphone-Native%20Bidirectional%20Tactile%20Multimodal%20Large%20Language%20Models.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7vetewxypj63g.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:21:19Z",
      "native_id": "23494137",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23494137"
    }
  ],
  "subjects": [],
  "title": "Smartphone-Native Bidirectional Tactile Multimodal Large Language Models: A Unified Framework for Tactile Perception, Reasoning, Generation, and Physical Feedback",
  "title_text": "Smartphone-Native Bidirectional Tactile Multimodal Large Language Models: A Unified Framework for Tactile Perception, Reasoning, Generation, and Physical Feedback",
  "type": "preprint",
  "updated_at": "2026-11-03T12:21:19Z",
  "url": "https://research.draconitic.com/paper/7vetewxypj63g",
  "venue": "Zenodo",
  "versions": []
}