• Keynote Speaker: Victoria Vesna

Professor @ UCLA Design | Media Arts; Director, Art|Sci Center

• Bio.: Victoria Vesna is a media artist and professor at UCLA whose work bridges art, science, and technology. As Director of the Art|Sci Center, she leads cross-disciplinary projects exploring data, sound, and immersive media to foster public engagement with emerging technologies and their cultural impact. 

• Title: Culture-Aware AI Arts: Dialogues Between Data, Bodies, and Metaverse Spaces

  • Abstract: This talk surveys three decades of art–science collaborations that use databases, telepresence, and AR/VR installations to craft culturally aware experiences. I will show how artistic practice can reveal hidden biases in datasets and models, stage consent-aware pipelines for generative media, and create participatory works where audiences co-produce meaning with AI. Case studies from the Art|Sci Center highlight curatorial strategies, provenance/watermarking, and community-based evaluation that make metaverse artworks respectful and sustainable. The goal is to outline practical methods that help AI “see one world through many lenses” while remaining accountable to people and places.

• Invited Talk 1: Haley Marks

Project Scientist @ California NanoSystems Institute (UCLA)

• Bio.: Haley L. Marks is a Project Scientist at the California NanoSystems Institute (UCLA), working with the Advanced Light Microscopy & Spectroscopy program. Her work focuses on quantitative imaging pipelines that combine fluorescence, Raman, and hyperspectral microscopy with controlled illumination and calibration. She collaborates with researchers, museums, and cultural institutions to translate lab-grade measurement methods into practical digitization workflows, supporting trustworthy metadata for description, retrieval, and generative AI applications.

• Title: Spectral & Microscopy-Driven Pipelines for Trustworthy Digitization of Cultural Artifacts

  • Abstract: We present practical imaging workflows that combine fluorescence, Raman, and spectral microscopy with controlled photometric capture to digitize cultural artifacts with faithful color, texture, and condition metadata. These measurements feed multimodal models (VLM/LLM) to improve grounding for description, retrieval, and generation while reducing cultural bias. The talk outlines illumination control, calibration, and validation protocols, and shows how lab-grade instruments can be translated into accessible kits for museums and community archives.

• Invited Talk 2: Ziyu Wan

Member of Technical Staff @ Microsoft AI

• Bio.: Ziyu Wan works on photorealistic visual reconstruction and generation at Microsoft AI. His recent projects span diffusion-based image/video generation, view-consistent reconstruction, and editing with geometry/appearance control. He is broadly interested in bridging reconstruction and generation so that models can recover faithful 3D/4D structure while remaining controllable and efficient for real applications.

• Title: Towards Photorealistic Visual Reconstruction and Generation

• Abstract: This talk overviews recent methods that unify reconstruction and generation for photorealistic results. We begin with geometry-aware priors and camera-consistent conditioning that preserve structure across views and time. Building on these, diffusion models are adapted with scene representations (depth/normal/feature fields) and lightweight controllers for text, masks, and layout, enabling faithful novel-view synthesis and editable outputs. I will discuss strategies for temporal and multi-view consistency, reducing artifacts such as flicker and texture drift, and improving efficiency with distillation and hybrid rasterization/denoising pipelines. Finally, I will show demos that connect these techniques to interactive editing and metaverse scenarios, where users can reconstruct, relight, and modify dynamic scenes while keeping realism and identity.

• Invited Talk 3: JungHyuk Im

CEO @ Innerverz

• Bio.: JungHyuk Im is the CEO of Innerverz, where he leads R&D and production pipelines that integrate generative AI with modern animation and virtual-production workflows. His team focuses on data-driven asset creation, character and motion generation, and real-time toolchains that bridge pre-production, layout, and post. He works closely with artists and engineers to translate research advances into scalable studio practices, emphasizing creative control, consistency, and rights-respecting content management across projects.

• Title: AI-Driven Animation

  • Abstract: This talk presents recent advances in integrating generative AI into real-time animation and virtual production workflows for interactive environments. We introduce AI-driven pipelines for character, motion, and scene asset generation that enable controllable and scalable content creation across pre-production and post-production stages. By combining multimodal generative models with layout-aware animation systems, these workflows allow artists and engineers to collaboratively construct dynamic digital characters and environments that remain editable throughout the production cycle. The talk further discusses how data-centric animation systems can support interactive storytelling and embodied agents in immersive 3D and 4D metaverse spaces. Finally, we highlight the importance of creative control, stylistic consistency, and rights-aware content management in deploying generative animation tools for culturally grounded interactive media applications.

• Invited Talk 4: Marcos V. Conde

Ph.D. @ University of Würzburg

• Bio.: Marcos V. Conde obtained Ph.D. degree in Artificial Intelligence and Computer Vision at the University of Würzburg, advised by Prof. Radu Timofte. He is also Kaggle Grandmaster at H2O.ai. Since 2024, he is Chief Scientific Advisor at Fundación CIDAUT in Spain, working on cameras and robots with a brilliant team of students. During his PhD (2022-2025), he was Computer Vision Scientist at Sony PlayStation, working on Graphics, Super-Resolution (like DLSS), and Streaming. During 2020-21, he was Research Intern at Huawei Noah’s Ark Lab (London), and received the best intern award for my work on neural ISPs and RAW processing supervised by Dr. Eduardo Pérez-Pellitero, while undergrad.

• Title: Controllable Neural Photography

  • Abstract: This talk explores recent developments in controllable neural photography for interactive visual reconstruction and generation in immersive environments. We introduce methods that integrate neural image signal processing, computational photography, and learning-based rendering to recover geometry, appearance, and photometric consistency from sparse or degraded observations. By enabling fine-grained control over lighting, viewpoint, and scene attributes, these techniques support real-time editing and faithful novel-view synthesis across space and time. The talk further discusses how controllable reconstruction pipelines can serve as foundational components for interactive metaverse systems, allowing users to capture, relight, and modify dynamic scenes while preserving realism and identity. Finally, we examine how these approaches contribute to multimodal 2D to 4D perception and generation, bridging low-level imaging with agentic visual interaction in culturally-aware immersive applications.