From the Art Gallery to Technical Workshops, the conference explores how artificial intelligence augments the work of artists, researchers, and technologists
LOS ANGELES, July 17, 2026 /PRNewswire/ — Artificial intelligence is not confined to a single track at SIGGRAPH 2026. It runs through nearly every program at the conference, from interactive installations and peer-reviewed research to hands-on workshops, community discussions, and industry-led training. Taking place 19–23 July at the Los Angeles Convention Center, the world’s leading conference on computer graphics and interactive techniques shows how AI is being used to expand, not replace, human creativity.
“AI is showing up in a number of ways, from the research spectrum to the artistic side of the conference, where it isn’t used as a means of replacement but as a means to augment the work being done by the talented artists and technologists who attend,” said SIGGRAPH 2026 Conference Chair Chris Redmann. “The lines between computer graphics, physics, and AI are becoming blurred, and that opens up new horizons and pathways for computer graphics research and new modes of interactivity, where the physical world and the digital world become more complementary.”
Featured Experiences at SIGGRAPH 2026
Among the standout AI sessions this year, the Art Gallery installation “The Long Fall: A Descent Into the Ocean’s Living Memory” traces the microscopic labor of plankton, the silent architects of Earth’s climate, as visitors descend from the White Cliffs of Dover to drifting marine snow. Built on Gravity Machine data gathered across 18 expeditions with Stanford’s Prakash Lab, the work features a “plankton instrument” and narration by the AI-revived voice of Rachel Carson. Artists include Jiabao Li with Northeastern University and the University of Tokyo, Manu Prakash with Stanford University, Will Tallent with The University of Texas at Austin, and Michael Bruner with Texas A&M University.
Also in the Art Gallery, “Diffusion TV” by Sihwa Park with York University demystifies AI diffusion models through a nostalgic CRT television. By turning the set’s knobs and antenna, viewers move across three channels: extinct animals of the past, endangered species of the present, and speculative AI-generated creatures of the future, watching chaotic data resolve into recognizable forms.
The Art Paper “Light Architecture: Translating the AI Black Box Into Immersive Experience” by Yiyun Kang with Yiyun Kang Studio and the Korea Advanced Institute of Science and Technology physically translates invisible algorithmic structures into kinetic light and spatial audio, offering a sensory alternative to traditional explainable AI.
In the Spatial Storytelling program, “Dog Walk: Narrating Human-AI Alignment Through Companion Robots” documents two artist-researchers co-parenting a pair of robot dogs, blending human and machine perspectives to explore authenticity, embodiment, and synthetic companionship. Contributors include Robert Twomey, University of California, San Diego, and Jesse Fleming, The Awareness Lab, both involved with the Arthur C. Clarke Center for Human Imagination.
Hands-on Courses invite attendees to work directly with emerging tools. In “Dreaming in 4 Dimensions: Generating Media With Gemini, Genie, and Veo”, Google DeepMind engineers, led by Paige Bailey with DeepMind and Google, move attendees beyond static pixels into explorable, playable worlds, working hands-on with NanoBanana Pro for reasoned concept art, Veo 3.1 for video generation, and Genie 3 to turn images and text into interactive worlds. In “Hands-on Programming and Running Quantum Teleportation”, Andrew Glassner teaches participants to write and run quantum computing code, then program the quantum teleportation algorithm on a high-quality simulator to transfer the state of a quantum bit to a partner, who decodes it to reveal a secret message.
Technical Workshops: Where Humans and AI Create Together
Technical Workshops anchor much of the conference’s AI programming. “Human–AI Co-Creation in Generative Art: Graphics Methods, Systems, and Applications” examines AI not as an automation tool but as a creative partner supporting exploration, iteration, and artistic expression, with speakers from NVIDIA, Brown University, the University of Washington, Massachusetts Institute of Technology (MIT), the Hong Kong University of Science and Technology (Guangzhou), the University of California Santa Barbara, and Stanford University. “Lines and Minds: Visual Abstraction in Art, Psychology, and Computer Graphics” asks what role abstraction plays in how humans and AI create together, featuring cartoonist and theorist Scott McCloud alongside researchers from Stanford University, MIT CSAIL, and Adobe Research.
The 10th installment of “AI for Creative Visual Content Generation, Editing and Understanding” brings together academic researchers and the technical architects behind current video generation models to bridge the gap between raw visual tokens and the language of cinema. “Graphics4Science 2026: Graphics for Cross-Scale Reliable Scientific Instruments” turns to AI-enabled scientific discovery, from computational imaging to generative modeling for molecular structures, while “Differentiable Physics for Graphics and AI” explores how differentiable simulation is transforming graphics, robotics, 3D vision, design, and fabrication.
“AI is an exciting thing, not something to be feared and not something to be overhyped. It’s really cool technology that allows us to do things we haven’t done before, and SIGGRAPH is well-positioned to explore AI without the hype and fearmongering of the mainstream,” said SIGGRAPH 2026 Technical Workshops Chair Adam Bargteil.
From Community Conversations to the Classroom and Industry Floor
Community members gather to lead dynamic Birds of a Feather sessions that spark conversations on emerging themes and cross-disciplinary innovations shaping the future of computer graphics, interactive techniques, and beyond. AI threads through this year’s lineup. “The Last 20%: Getting GenAI to a Deliverable Frame” brings together artists, pipeline engineers, and tool builders from Foundry, RSP, and NVIDIA to explore pipelines that pair the speed of AI with the control of traditional workflows while keeping artists in command, while “Controlling the Frame: AI VFX, Generative Video, and the Future of Compositing” asks how much control artists actually retain as relighting, background transformation, and look development increasingly happen after capture. “Machine Choreographies: AI, Dance, and the Future of Embodied Performance” invites artists, technologists, and researchers to examine how AI is reshaping movement, authorship, and the body in motion. And the live-demo-driven “AI3D Frontiers: AI for 3D BOF #4” continues its run as a home for hackers, artists, researchers, and independent creators building the strange, early, hybrid things that define what AI for 3D is becoming.
In the classroom, AI takes center stage on Educator’s Day, Monday, 20 July, where half of the day’s six sessions confront how the technology is reshaping teaching. The panel “The AI Inflection Point: What It Actually Means for the Next Generation of 3D Artists”, moderated by Alwyn Hunt with Adobe, brings together a university professor, a self-taught independent creator, a CG production veteran, and an Adobe industry strategist to ask what educators should focus on as AI handles more of the technical execution students once spent years learning. In “NVIDIA: How AI is Changing Education”, Jacob Liberman with NVIDIA leads a discussion on how generative AI and large language models are personalizing learning, accelerating skill development, and democratizing access to education, drawing on NVIDIA’s Deep Learning Institute and the AI-powered study platform Studyfetch. And in “Shaping Future Storytellers: Integrating Advanced 3D, AI and VP Workflows”, Juan Salazar with Foundry makes the case for teaching the core concepts behind the craft, not just the technical steps, and for training artists who know how to evaluate and direct their tools.
On the industry side, NVIDIA dedicates a full day to the convergence of graphics and AI with NVIDIA Physical AI Day on Tuesday, 21 July. Ming-Yu Liu with NVIDIA opens with “World Models: The Frontier of Physical AI, Unlocked By Graphics”, introducing the open frontier world model NVIDIA Cosmos 3 and exploring why 3D graphics is central to AI’s ability to see, understand, generate, and simulate the world.
Together, the day’s sessions tell the story of how a physical AI world gets built. Aaron Luk with NVIDIA starts with the data, showing how OpenUSD gives AI agents and developers 3D scenes they can direct, inspect, and trust. Jonathan Stephens with Lightwheel and Steven Ren with Palatial turn those scenes into simulation-ready worlds, and then the worlds go to work: in real-time digital twins helping Rivian accelerate automotive design, in a physics-aware simulation app that Damien Fagnou with NVIDIA assembles live alongside AI agent co-host Lexi, and in autonomous vehicle simulation that renders drivable, photorealistic worlds in real time on a single GPU. Miles Macklin with NVIDIA introduces Newton, the open-source physics engine underneath it all, and a career growth panel with voices from NVIDIA, Keywords Studios, and Miris brings the story back to people, tracing how 3D graphics skills carry into careers in robotics, AI, simulation, and digital twins.
The conversation continues well beyond the convention center. ACM SIGGRAPH Blog posts, including “AI Is Not Just About Machines — It’s About People” and “Tracing Life From Above”, trace how the community is thinking about AI’s role in creative work. To explore the full AI lineup, visit the conference schedule and register now for SIGGRAPH 2026.
About ACM, ACM SIGGRAPH, and SIGGRAPH 2026
ACM, the Association for Computing Machinery, is the world’s largest educational and scientific computing society, uniting educators, researchers, and professionals to inspire dialogue, share resources, and address the field’s challenges. ACM SIGGRAPH is a special interest group within ACM that serves as an interdisciplinary community for members in research, technology, and applications in computer graphics and interactive techniques. The SIGGRAPH conference is the world’s leading annual interdisciplinary educational experience showcasing the latest in computer graphics and interactive techniques. SIGGRAPH 2026, the 53rd annual conference hosted by ACM SIGGRAPH, will take place live 19–23 July at the Los Angeles Convention Center.
SOURCE SIGGRAPH 2026