MLOW focuses on interactive metaverse systems that can perceive, communicate, and act within 3D/4D environments. Building such systems requires not only the technical foundations of AI and computer vision but also a deep consideration of the human-centric dimensions shaped by culture, affect, and artistic expression. MLOW provides an interdisciplinary venue where these perspectives converge—bringing together researchers to explore how interactive AI can operate meaningfully within immersive, socially and culturally grounded metaverse spaces.
More specifically, MLOW integrates two complementary dimensions:
(1) Technical Foundations for Interactive Metaverse AI — core advances in multimodal VLM/LLM grounding, 3D/4D perception, neural rendering, dynamic scene understanding, and embodied AI operating across visual, linguistic, and spatial modalities;
(2) Human & Cultural Dimensions of Metaverse Interaction — perspectives that examine how AI systems relate to cultural context, diversity, affect, creativity, and artistic expression, highlighted through our Art+AI demo track and cross-cultural interaction studies.
MLOW invites researchers, practitioners, and creators to share technical advances, human-centered insights, and creative explorations that push the boundaries of interactive AI in the metaverse. The workshop will feature keynote/invited talks by leading experts working across image processing, 3D/4D vision, and large-scale language/vision models. Participants will have opportunities to have an oral presentation, to engage in in-depth discussions to explore potential research collaborations. In addition to technical sessions, MLOW will host an Art+AI demo and exhibition track, highlighting creative, affective, and culturally grounded metaverse experiences that complement the workshop’s interdisciplinary focus.