• 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 UCLA Art|Sci Center, she leads interdisciplinary collaborations exploring data, sound, biotechnology, networked systems, and immersive media. Her work has been exhibited internationally and has received numerous awards. She is also North American Editor of AI & Society: Journal of Knowledge, Culture, and Communication  (Springer/Verlag, UK). Through her research and artistic practice, she invites audiences to engage critically and creatively with the cultural, social, ethical, and environmental implications of emerging technologies. 

• Title: Across Scales and Cultures: Art–Science Perspectives on AI and Immersive Worlds

  • Abstract: This keynote draws on three decades of art–science collaborations using databases, telepresence, immersive environments, and AR/VR to create culturally responsive experiences. A central focus is scale—from the microscopic and atomic to the planetary—and the ways collaborations with microscopists, physicists, environmental scientists, and other researchers reshape how data, bodies, and technological systems are perceived. Selected artistic projects will be examined to show how artistic practice can reveal biases embedded in datasets and computational systems while opening alternative approaches to intelligence, embodiment, and participation. Case studies from the UCLA Art|Sci Center will highlight collaborative methods grounded in cultural awareness, authorship, and accountability, proposing ways for AI to engage one world through many lenses without reducing difference to categories or stereotypes. 

• Invited Talk 1: Haley Marks

Project Scientist @ California NanoSystems Institute (UCLA)

• Bio.: Haley Marks, PhD is a project scientist at the California NanoSystems Institute (UCLA), supporting the Advanced Light Microscopy & Spectroscopy (ALMS) shared resource facility. Her work focuses on quantitative imaging pipelines combining correlative imaging modalities including second harmonic generation, fluorescence lifetime imaging, Raman scattering, super-resolution, and multiphoton microscopy. Working across dozens of research groups, she builds customized image segmentation and analysis workflows which turn raw acquisitions into reproducible, metadata-rich measurements, producing trustworthy datasets for specimens ranging from clinical biopsies to cultural artifacts.

• Title: Going Beyond RGB Colorspace Using Spectroscopy, Microscopy, and Machine Learning for Quantitative Digitization of Biological and Cultural Specimens

  • Abstract: Conventional digitization of microscopic samples typically record appearance under a single illumination condition, and on one dimensional scale. Herein we describe correlative imaging workflows which instead recover chemically, spectrally, and structurally specific measurements using a combination of microscopy techniques. Second harmonic and fluorescence lifetime imaging with phasor analysis separate free and protein-bound metabolites without exogenous labels from extracellular matrix components, providing metabolic readout in live cells, organ-on-chip constructs, and tissue biopsies under multiphoton excitation. For additional chemical specificity, Raman scattering returns molecular and mineral fingerprints, applied to samples ranging from kidney stones to pigment identification for painting authentication, while second harmonic generation and correlative atomic force microscopy resolve nanoscale structural organization. As accurate quantification depends heavily on calibrated excitation and detection systems and on spectral standards in order to keep measurements comparable across instruments and sessions, random forest pixel classifiers and U-Net segmentation convert these acquisitions into per-object measurements at scale, producing the confidence in image measurements which multimodal models require for trustworthy artifact description and retrieval.

• 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 End-to-End Animation Workflows

  • Abstract: This talk presents recent advances in integrating generative AI into 2D animation production workflows. We introduce an end-to-end AI-driven pipeline from art style & concept building, characters and location asset generations to a reference-based scene & video generation workflow across pre-production and post-proudction stages. The talk further discusses about recent video generation models and their animation generation capabilities and characteristics, as well as model curation and prompting strategies according to targetted purposes.

• 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: Photorealistic and Controllable Imaging Models

  • Abstract: The advances in deep learning and neural networks provide powerful solutions for computational photography problems such as denoising, super-resolution and deblurring. However, these methods often lack control and behave as "black boxes", which is a huge limitation for industry applications and user experience. As users start to interact more with AI agents through prompts to control complex processes, a similar process occurs in image editing. In this talk, we will review some controllable neural methods for image signal processing, restoration and enhancement, aiming at providing reliable and user-friendly applications.