Key Takeaways
- NVIDIA’s sponsored keynote at SIGGRAPH 2026 will unveil cutting-edge developments in neural rendering, world models, and AI-driven simulation.
- Industry leaders Neil Ashton, Ming-Yu Liu, and Edward Liu will showcase how these technologies are transforming digital world creation across various sectors, from creative tools to robotics.
- The conference will also feature deep dives into major film VFX (Avatar, The Mandalorian), scientific visualization (Artemis II), and artist-centered AI animation workflows.
The future of computer graphics and artificial intelligence is set to unfold dramatically at SIGGRAPH 2026, with NVIDIA Neural Rendering at the forefront. NVIDIA, a pioneer in GPU technology and AI innovation, has announced a highly anticipated keynote presentation titled “Next Era of Graphics — Neural Rendering, World Models, and Simulation.” This pivotal session promises to reveal groundbreaking advancements that are poised to redefine how digital worlds are conceived, built, and interacted with across a myriad of industries. The conference itself runs from July 19-23 in Los Angeles, with the keynote scheduled for Monday, July 20, at 3:45 p.m. PDT.
This year’s keynote will feature three distinguished leaders from NVIDIA’s Research and Engineering divisions: Neil Ashton, Ming-Yu Liu, and Edward Liu. Together, they will delve into the profound impact of neural rendering techniques, the evolution of world models, and innovative simulation methods that are not just driven by AI, but increasingly built by AI. Attendees can expect a deep dive into recent research examples and compelling demonstrations illustrating how these sophisticated technologies are fundamentally changing the landscape for creative professionals, industrial designers, robotics engineers, and developers of autonomous systems.
NVIDIA’s Vision: The Next Era of Graphics with Neural Rendering
The core of NVIDIA’s keynote will revolve around pushing the boundaries of what’s possible in digital creation. The synergy between neural rendering, sophisticated world models, and advanced simulation is creating an unprecedented toolkit for artists and engineers alike. These technologies promise to unlock new levels of realism, interactivity, and efficiency.
The Architects of Innovation: Meet NVIDIA’s Keynote Speakers
Guiding the audience through this transformative journey will be three titans of tech innovation, each bringing a unique perspective to the table.
Neil Ashton: Pioneering AI Physics and Agentic AI
Neil Ashton, a Distinguished Engineer at NVIDIA, is a driving force behind AI physics and agentic AI, particularly for computational engineering. A Fellow of the Institution of Mechanical Engineers, Ashton’s work spans accelerated simulation, scientific machine learning, and physical AI. His contributions are crucial in integrating advanced AI methods into practical workflows across aerospace, automotive, and other industrial sectors.
Ashton’s pioneering efforts include developing the first open datasets for complete aircraft (HiLiftAeroML) and road-vehicle configurations (DrivAerML). His current research explores AI agents, physics foundation models, surrogate modeling, and accelerated digital twins. The focus is on creating systems capable of reasoning about, simulating, and optimizing complex physical designs, a critical step towards truly intelligent digital environments. Before joining NVIDIA, Ashton held significant roles at AWS, NASA, Formula 1, and the University of Oxford, underscoring his diverse expertise.
Ming-Yu Liu: Building a Physics-Grounded ‘Matrix’ with Generative AI
IEEE Fellow Ming-Yu Liu leads the NVIDIA Cosmos Lab, previously known as the Deep Imagination Research group. His team is dedicated to generative AI for Physical AI, specifically developing world foundation models that empower machines to simulate, reason about, and interact with the physical world. Liu’s ambitious vision is to construct a physics-grounded “Matrix” for robots, a digital realm where AI can learn and operate with unparalleled fidelity.
Liu’s work seamlessly bridges cutting-edge research with real-world platforms, impacting millions. His team’s innovations power key NVIDIA technologies such as Cosmos, Edify, Canvas, and Maxine. Furthermore, they have made substantial contributions to state-of-the-art text-to-image, text-to-video, and text-to-3D models, showcasing the breadth of their influence on generative AI. Prior to NVIDIA, Liu conducted research at Mitsubishi Electric Research Labs and earned his Ph.D. from the University of Maryland, College Park.
Edward Liu: Redefining Real-Time Graphics with DLSS and NVIDIA Neural Rendering
As the Director of Applied Deep Learning Research at NVIDIA, Edward Liu is at the forefront of AI for real-time graphics and generative visual computing. He has been instrumental in transforming real-time graphics through AI, notably leading advancements in the acclaimed DLSS (Deep Learning Super Sampling) technology suite. DLSS has become an industry standard, serving as a defining differentiator for RTX products by significantly boosting performance and image quality.
Liu’s current endeavors include pioneering DLSS 5 Neural Rendering, a significant evolution that promises even more immersive and visually stunning real-time experiences. His broader research focuses on shaping the future of AI-powered interactive visual computing, ensuring that gamers, creators, and professionals benefit from the most advanced graphical capabilities. His work directly enhances the impact of NVIDIA Neural Rendering on interactive applications.
Keynote and Speaker Highlights at SIGGRAPH 2026
| Feature/Speaker | Role & Focus Area | Key Contributions/Technologies |
|---|---|---|
| Neil Ashton | Distinguished Engineer, AI Physics & Agentic AI | AI physics, agentic AI, computational engineering, HiLiftAeroML, DrivAerML, digital twins |
| Ming-Yu Liu | IEEE Fellow, Lead of NVIDIA Cosmos Lab | Generative AI, world foundation models, Cosmos, Edify, Canvas, Maxine, text-to-3D |
| Edward Liu | Director of Applied Deep Learning Research | AI for real-time graphics, generative visual computing, DLSS technology, DLSS 5 Neural Rendering |
| Keynote Title | Next Era of Graphics | Neural Rendering, World Models, Simulation |
| Event | SIGGRAPH 2026 Keynote | Monday, July 20, 3:45 p.m. PDT |
Beyond the Keynote: A Glimpse into SIGGRAPH 2026’s Rich Program
While NVIDIA’s keynote promises to be a highlight, SIGGRAPH 2026 offers an extensive program filled with cutting-edge research, artistic showcases, and behind-the-scenes looks at major productions. The conference is a melting pot of innovation, covering everything from experimental animation to industrial VFX.
The Computer Animation Festival: A Global Showcase
The renowned Computer Animation Festival will once again captivate attendees with screenings of the Electronic Theater and Animation Theater. These sessions provide multiple avenues to experience emerging animation trends from around the globe. A selection of top films will also be featured in the SIGGRAPH Computer Animation Festival Traveling Show, extending its reach to campuses, festivals, and communities worldwide. This festival is a testament to the vibrant and ever-evolving art form of animation, often showcasing techniques that will become industry standards.
Production Sessions: Unveiling Creative Masterpieces
The Production Sessions program is a perennial favorite, offering unparalleled behind-the-scenes insights into the creation of films, immersive experiences, and scientific visualization projects. These sessions provide invaluable learning opportunities, detailing the complex pipelines and creative problem-solving employed by leading studios.
Wētā FX Presents: Avatar: Fire and Ash
Wētā FX and Lightstorm Entertainment will take attendees on a journey back to Pandora, examining the creation of over 3,100 shots for Avatar: Fire and Ash. This presentation will highlight the intricate blending of extensive native stereo photography with fully digital, performance-captured characters. The team will also discuss how they meticulously handcrafted elements of the world, including creatures, clans, and the film’s titular fire, which was created using Kora, a new addition to Wētā FX’s global simulation framework, Loki. A proprietary facial system, designed to preserve each actor’s performance, was used to create more than 2,500 facial motion shots for 30 speaking characters.
NASA’s “Visualizing the Moon for Artemis II”
NASA will present an awe-inspiring session on “Visualizing the Moon for Artemis II.” This presentation will demonstrate how cinematic scientific visualization, built from publicly available datasets and high-end 3D rendering, was used to recreate the exact lighting conditions astronauts will encounter on the far side of the Moon. This critical work has been instrumental in planning observations and training the Artemis II crew for the first crewed flight to the Moon since Apollo 17, showcasing the vital role of graphics in space exploration.
Pixar Animation Studios: The Making of Disney and Pixar’s Hoppers
Pixar Animation Studios will share insights into “We’re All In This Together: The Making of Disney and Pixar’s Hoppers.” This session will focus on the cross-departmental pipeline that allowed physical simulation and artistically directed stylization to coexist harmoniously in every shot. The presentation will explore how the team balanced broad comedy, suspense, and the beauty of nature photography, all while maintaining a consistent visual language. For more on how studios innovate their animation and VFX pipelines, consider reading about Foundry Unleashes AI-Powered SmartRoto Plugin for Nuke: Revolutionizing VFX Rotoscoping.
Industrial Light & Magic: Bringing The Mandalorian and Grogu to Life
Industrial Light & Magic (ILM) will present “Bringing The Mandalorian and Grogu to Life: Virtual Production, Creatures, and VFX Innovations.” This session will detail the innovative use of real-time technology, virtual production workflows, and established visual effects techniques to bring the latest Star Wars feature to the big screen. ILM’s presentation is expected to be a masterclass in modern filmmaking, blending practical and digital effects seamlessly.
Google DeepMind: Artist-Centered, AI-Assisted Expressionistic Animation
Google DeepMind animation veterans and researchers will present “Dear Upstairs Neighbors: Artist-Centered, AI-Assisted Expressionistic Animation.” This session will cover how artist-driven, AI-assisted workflows shaped an expressionistic, painterly short film. It highlights a crucial trend where artists remain in control as both creators and co-designers throughout the AI-powered animation process, showcasing the collaborative potential of AI in creative fields.
Valerie Bernard, SIGGRAPH 2026 Production Sessions chair, emphasizes the comprehensive nature of these sessions: “Production Sessions cover the full production, from the very start of the concept art and the story all the way to the end, giving you a really great general view of the entire pipeline. We get to learn about so many creative challenges that teams had to solve by getting multiple departments to work together. They are for everyone.” Bernard adds that these sessions are invaluable for both newcomers and industry veterans, providing insights and inspiration.
SIGGRAPH 2026, the 53rd annual conference hosted by ACM SIGGRAPH, continues to be the premier venue for advancements in computer graphics and interactive techniques. ACM, the Association for Computing Machinery, is a leading educational and scientific computing society, and its special interest group (ACM SIGGRAPH) is dedicated to fostering research, technology, and applications in this dynamic field. Innovations like those in NFB Pioneers Next-Gen Gaussian Splatting Animation Workflows at SIGGRAPH 2026 further demonstrate the breadth of groundbreaking work presented at this esteemed conference.
The Future is Now: Impact of NVIDIA’s Innovations
The advancements in NVIDIA Neural Rendering, world models, and AI-driven simulation represent more than just technological progress; they signify a paradigm shift in how we interact with and create digital realities. From hyper-realistic game environments to highly accurate industrial simulations and intelligent autonomous systems, these innovations are laying the groundwork for a future where the line between the physical and digital becomes increasingly blurred. NVIDIA’s commitment to pushing these boundaries, as evidenced by the expertise of its research leaders, ensures that the “Next Era of Graphics” will be defined by unprecedented levels of realism, interactivity, and creative freedom. For more detailed information on NVIDIA’s ongoing research, visit the official NVIDIA Research page, and explore the broader scope of the conference at ACM SIGGRAPH.
Frequently Asked Questions (FAQs)
What is neural rendering?
Neural rendering is an advanced graphics technique that uses neural networks (a type of AI) to synthesize images and videos. Instead of traditional rendering pipelines that rely on explicit geometric models and material properties, neural rendering can learn to generate highly realistic visual content directly from data, often achieving photorealism with greater efficiency and flexibility. It’s a key component of next-generation graphics, enabling features like NVIDIA’s DLSS and realistic digital humans.
How do ‘world models’ contribute to AI and simulation?
World models in AI refer to computational representations that allow an AI system to understand, predict, and reason about its environment. For simulation, these models create a digital twin of the physical world, enabling AI agents (like robots or autonomous vehicles) to learn and test actions in a safe, controlled virtual space. This allows for rapid iteration and training, leading to more robust and intelligent AI systems that can then operate effectively in the real world, as envisioned by NVIDIA’s Cosmos Lab.
What is the significance of NVIDIA’s DLSS technology?
NVIDIA’s Deep Learning Super Sampling (DLSS) is a revolutionary AI rendering technology that uses deep learning to boost graphics performance. It renders frames at a lower resolution and then uses AI to upscale them to a higher resolution, intelligently adding detail to create a sharper, more realistic image. This significantly improves frame rates in games and applications without sacrificing visual quality, making high-fidelity graphics more accessible and pushing the boundaries of real-time rendering, especially with advancements like DLSS 5 Neural Rendering.
What other major events are happening at SIGGRAPH 2026 beyond the keynote?
Beyond NVIDIA’s keynote, SIGGRAPH 2026 features a diverse program. Key events include the Computer Animation Festival, showcasing global animation trends; Production Sessions offering behind-the-scenes looks at major film VFX (e.g., Avatar: Fire and Ash, The Mandalorian) and scientific visualizations (e.g., NASA’s Artemis II); and presentations on artist-centered AI animation from entities like Google DeepMind. The conference also includes an exhibition, research presentations, and educational programs, making it a comprehensive hub for computer graphics and interactive techniques.
