What is NVIDIA doing at SIGGRAPH 2026?

NVIDIA will offer hands-on training labs, technical sessions, and community events at SIGGRAPH 2026, July 19-23 at the L.A. Convention Center. Highlights include Neural Rendering Day (August 12), Physical AI Day (August 13), NVIDIA Research talks by Sanja Fidler, Aaron Lefohn, and Ming-Yu Liu, and research paper presentations covering neural rendering, physical AI, and generative AI.

What are the NVIDIA hands-on labs at SIGGRAPH 2026?

NVIDIA will offer hands-on training labs at SIGGRAPH 2026 covering AI, research, OpenUSD, and more. Sign up to be notified when training lab registrations open at nvidia.com/en-us/events/siggraph/.

Who are the NVIDIA Research speakers at SIGGRAPH 2026?

NVIDIA AI research leaders Sanja Fidler, Aaron Lefohn, and Ming-Yu Liu will deliver a Special Address at SIGGRAPH 2026, covering breakthroughs in computer graphics and physical AI, including faster synthetic data generation and AI-powered content creation.

How do I register for NVIDIA events at SIGGRAPH 2026?

Registration for SIGGRAPH 2026 is available at Register . To be notified about NVIDIA-specific events, labs, and updates, use the Notify Me form at nvidia.com/en-us/events/siggraph/.

NVIDIA at SIGGRAPH 2026

July 19–23
L.A. Convention Center
Los Angeles

Watch On Demand

Overview
Announcements
Special Events
Research Presentations
Partners
Programs
Careers

Overview
Announcements
Special Events
Research Presentations
Partners
Programs
Careers

Watch On Demand

At SIGGRAPH 2026, NVIDIA showcased the research, tools, and breakthroughs pushing graphics into its next era—from neural rendering and simulation to AI that's changing how worlds are built and understood.

Watch On Demand

Read Blog Recap

NVIDIA Keynote

Watch the replay of NVIDIA AI research and engineering leaders Neil Ashton, Edward Liu, and Ming-Yu Liu to experience the latest advances shaping computer graphics and simulation. They explored breakthrough neural rendering techniques, progress in developing world models, and simulation methods for AI, built by AI.

Through recent research examples and demos, they showcased how these technologies are changing the way digital worlds are built, rendered, and used across every domain. These include everything from creative tools and industrial design to robotics and autonomous systems.

Watch Now

Neil Ashton, Edward Liu, and Ming-Yu Liu

Announcements

Physical AI

NVIDIA Puts AI Agents to Work Building Simulation-Ready 3D Worlds

NVIDIA Agent Toolkit expands with Omniverse™ libraries, giving AI agents tools to bring physical AI capabilities into existing applications, including a new NVIDIA blueprint for integrating Omniverse libraries in Blender.

Read the Press Release

Media and Entertainment

AI Agents Expand Creative Tools to Millions

Leading creative applications are opening Model Context Protocol connections that enable AI agents to understand and act directly within environments where production work already happens.

Read the Blog

Media and Entertainment

NVIDIA AI for Media Helps Newsrooms Detect Synthetic Video

As concerns about video authenticity increase among global news audiences, NVIDIA helps support source verification, editorial vetting, and media integrity.

Read the Blog

Physical AI

Now Openly Available, NVIDIA Cosmos 3 Edge for Local Physical AI

NVIDIA Cosmos 3 Edge brings frontier world models for physical AI to the edge. A 4-billion-parameter omnimodel optimized for memory-efficient deployment on NVIDIA Jetson, NVIDIA RTX PRO and NVIDIA DGX systems, as well as GeForce RTX GPUs.

Read the Blog

Agentic AI

NVIDIA NemoClaw on DGX Station Brings Secure, Specialized AI to Deskside Computers

NemoClaw on DGX Station gives designers and engineers a local agent stack that uses specialized tools, data and workflows to keep projects moving 24/7.

Read the Blog

Physical AI

NVIDIA Research Brings Computer Graphics Into Real-Time Systems for World Generation and Physical AI

NVIDIA Research is turning computer graphics into real-time systems that generate virtual worlds and drive physical AI, grounded in 3D, governed by physics and directed by creators.

Read the Blog

Special Events

Virtual Incision and Amazon Robotics

Physical AI Day

Tuesday, July 21, 9 a.m.–5 p.m. PT

Connect with developers and researchers exploring how pixels become real-world action. You'll learn how NVIDIA research in neural rendering, world foundation models, generative simulation, and OpenUSD is advancing physical AI for robotics, autonomous vehicles, and industrial digital twins.

Watch On Demand

RTX Rendering Day

Wednesday, July 22, 9 a.m.–5 p.m. PT

Explore the latest advancements in neural rendering, real-time and production rendering with NVIDIA RTX PRO™ for visual effects, animation, virtual production, and design visualization. You’ll hear from leading artists, designers, and rendering technology companies.

Watch on Demand

AI In Production Day

Thursday, July 23, 9 a.m.–3 p.m. PT

Learn how developers and industry pioneers are using generative and agentic AI for real-world production.

Watch on Demand

Educators' Day

Monday, July 20, 11:45 a.m.–12:15 p.m. PT

AI has the potential to revolutionize how people teach and learn, but keeping up with the blistering pace of technological advancement is no small feat. In this session, we'll share how NVIDIA helps partners, customers, and teammates learn and grow.

Schedule at a Glance

Start Time	End Time	Session	Type	Location
10:30 a.m.	10:50 a.m.	OpenVDB: Major Changes to File Format, NanoVDB and Tools	ASWF Open Source Days
2:00 p.m.	5:15 p.m.	NVIDIA: Beyond 3D: From Real-World Objects to Digital Assets and Physical AI	Training Lab	403 A
3:45 p.m.	5:15 p.m.	How To Build End-To-End Physical AI Systems for Robots	Training Lab	408 A
4:25 p.m.	4:35 p.m.	A Reference Renderer for OpenUSD Interoperability	ASWF Open Source Days
4:35 p.m.	4:55 p.m.	OpenUSD Proposals Across Domains: Challenges and Methodology	ASWF Open Source Days

Start Time	End Time	Session	Type	Location
11:00 a.m.	12:00 p.m.	Educators' Day	Educator's Day	411
3:45 p.m.	4:45 p.m.	NVIDIA Keynote	Keynote	Hall K
5:30 p.m.	7:30 p.m.	NVIDIA Developer Meetup	Other	Registration Required

Physical AI Day

Start Time	End Time	Session	Type	Location
9:00 a.m.	9:50 a.m.	World Models: The Frontier of Physical AI, Unlocked By Graphics	Physical AI Day	502A
10:00 a.m.	10:20 a.m.	OpenUSD for AI Agents, Model-Driven Workflows, and 3D Graphics Pipelines	Physical AI Day	502A
10:30 a.m.	11:20 a.m.	Building SimReady 3D Worlds for Physical AI	Physical AI Day	502A
11:30 a.m.	11:50 a.m.	How to Develop a Real-Time 3D Digital Twin for Rapid Engineering Design	Physical AI Day	502A
1:00 p.m.	1:50 p.m.	Career Growth in Physical AI: Bringing 3D Graphics Skills into Robotics and Digital Twins	Physical AI Day	502A
2:00 p.m.	2:50 p.m.	Building Physics-Aware, RTX-Enabled Apps with NVIDIA Omniverse Libraries and AI Agents	Physical AI Day	502A
3:00 p.m.	3:50 p.m.	Autonomous Vehicle Simulation Technologies with NuRec, OmniDreams, 3D Gaussian	Physical AI Day	502A
4:00 p.m.	4:50 p.m.	Introduction to Newton: Open-Source GPU Physics for Robotics	Physical AI Day	502A

RTX Rendering Day

Start Time	End Time	Session	Type	Location
9:00 a.m.	9:20 a.m.	Applied Research for Ray Tracing Massive Scenes in Real Time	RTX Rendering Day	502A
9:30 a.m.	9:50 a.m.	From Viewport to Virtual Production: Real-Time Ray Tracing with Chaos Vantage	RTX Rendering Day	502A
10:00 a.m.	10:20 a.m.	From Pitch to Photorealism: Maxon’s RTX-Powered Solutions for Advertising and Archviz	RTX Rendering Day	502A
10:30 a.m.	10:50 a.m.	Rendering’s Next Frontier with OTOY	RTX Rendering Day	502A
11:00 a.m.	11:50 a.m.	Faster Creative Iteration with Autodesk Arnold	RTX Rendering Day	502A
1:00 p.m.	1:50 p.m.	Practical Advances in AI-Accelerated Ray Tracing	RTX Rendering Day	502A
2:00 p.m.	2:50 p.m.	GPU Rendering at Film Scale: Karma XPU in Production at Rodeo FX	RTX Rendering Day	502A
3:00 p.m.	3:50 p.m.	Real-Time Stylized Workflows: GPU Accelerated Creativity at ILM	RTX Rendering Day	502A
4:00 p.m.	4:50 p.m.	Building a GPU Production Renderer with OptiX at Netflix Animation Studios	RTX Rendering Day	502A
4:30 p.m.	5:00 p.m.	Advancing LED Virtual Production with Neural Rendering	RTX Rendering Day	502A

AI in Production Day

Start Time	End Time	Session	Type	Location
9:00 a.m.	9:50 a.m.	The Making of The Great Galactic War: Directing Generative Video in 3D	AI in Production Day	502A
10:00 a.m.	10:50 a.m.	The Making of Kök Börü: Where Untold Stories Find New Pipelines	AI in Production Day	502A
11:00 a.m.	11:50 a.m.	Making the Old Stories New: Innovative Dreams and Moses	AI in Production Day	502A
1:00 p.m.	1:50 p.m.	Making ChikaBOOM!: AI, Animation, and the Artist-Centered Production Pipeline	AI in Production Day	502A
2:00 p.m.	2:50 p.m.	The Making of Sentinel: How AI Infrastructure Tools are Reshaping Film Production	AI in Production Day	502A

Stream Demos From SIGGRAPH

Witness some of our most exciting work yet in Physical AI, robotics and autonomous vehicles.

Watch Now

NVIDIA Hands-On Labs

Develop your skills with training in AI, research, OpenUSD, and more by joining our hands-on labs.

Sponsored by:

Sunday, July 19
11 a.m.–12:30 p.m. PT
NVIDIA Lab Room, Room 502B

Dive into the world of high-performance graphics programming with this hands-on lab focused on developing and debugging real-time rendering and ray-tracing applications built with Vulkan and Direct3D 12. This lab teaches how to effectively use NVIDIA Nsight™ Graphics to inspect and debug frames to identify and diagnose common rendering bugs and performance blockers.

By the end of the lab participants will understand the direct connection between the tools and the graphics runtime, and will be prepared to use Nsight Graphics with their own applications. Key tools covered include the Graphics Debugger, Ray Tracing Inspector, Shader Debugger, and GPU Crash Dump Inspector.

See Session Details

First Offering:

Sunday, July 19
2–2:25 p.m. PT
NVIDIA Lab Room, Room 502B

Second Offering:

Monday, July 20
9–9:25 a.m.
NVIDIA Lab Room, Room 502B

This presentation offers a focused update on the state of NVIDIA's graphics developer tools and a look at how agentic AI workflows are shaping their future direction. Covering recent advances in Nsight Graphics, Nsight Systems, and Nsight Aftermath, the session highlights key improvements to debugging, profiling, and crash analysis capabilities alongside an exploration of where AI-driven automation is heading next.

Attendees will come away with a grounded understanding of the current tooling landscape and practical insight into the agentic AI features being built for graphics developers. This presentation is paired with two hands-on labs where participants will directly use and explore AI-assisted workflows.

See Session Details (First Offering)

See Session Details (Second Offering)

First Offering:

Sunday, July 19
2:30–4 p.m. PT
NVIDIA Lab Room, Room 502B

Second Offering:

Monday, July 20
9:30–11 a.m.
NVIDIA Lab Room, Room 502B

Modern graphics applications are getting increasingly difficult to debug. Ray Tracing, advanced rendering pipelines with neural rendering, GPU crashes, and performance bottlenecks often require developers to navigate large amounts of data before identifying the true source of a problem. At the same time, AI-powered tools are beginning to transform how developers investigate and understand complex systems.

In this hands-on lab, participants will enter the Hall of Mysteries, an interactive graphics debugging experience built around a series of realistic rendering and performance challenges. Using a preview of the in-development Nsight Graphics MCP (Model Context Protocol) server, participants will study a Vulkan application to investigate visual artifacts, analyze renderer behavior, diagnose GPU crashes, and optimize performance using professional graphics debugging workflows. Rather than following a scripted tutorial or traditional use of the tooling, participants will gather evidence, formulate hypotheses, inspect captures and traces, and verify conclusions through AI-guided investigation. Along the way, they will learn how AI-assisted workflows can accelerate debugging while preserving the reasoning and verification skills required to solve real graphics problems.

By the end of the lab, participants will have solved multiple graphics debugging challenges and gained practical experience using AI-assisted workflows to investigate and resolve issues in modern graphics applications.

See Session Details (First Offering)

See Session Details (Second Offering)

First Offering:

Sunday, July 19
4:15–5:15 p.m. PT
NVIDIA Lab Room, Room 502B

Second Offering:

Monday, July 20
11:15 a.m.–12:15 p.m.
NVIDIA Lab Room, Room 502B

This training lab offers graphics developers a look at the agentic future being built into Nsight Systems, with a focus on holistic analysis of CPU and GPU performance. Participants will work through hands-on scenarios where AI agents assist with performance analysis. The session bridges the gap between emerging model capabilities and the practical realities of real-time and offline graphics pipelines. Developers at all levels will gain actionable insight into how agentic AI workflows can be adopted today and what innovations are on the horizon.

See Session Details (First Offering)

See Session Details (Second Offering)

Monday, July 20
1:30–3 p.m. PT
NVIDIA Lab Room, Room 502B

In this lab, we’ll work hands-on across three core capabilities of NVIDIA Cosmos™ 3: reasoning, world generation, and action prediction. We’ll use Cosmos 3 Nano Reasoner to caption real robot video, generate augmentation prompts, and validate synthetic footage using chain-of-thought reasoning. We’ll then use Cosmos 3 and Cosmos-Transfer2.5 to synthesize and transform photorealistic video from those prompts, scaling training data without new recording sessions.

Finally, we’ll apply Cosmos 3 in different action modes to translate scene understanding into embodied control commands, completing the perceive → reason → act loop.

See Session Details

Tuesday, July 21
10:15–11:45 a.m. PT
Concourse Hall

This hands-on course introduces Slang, an open source, open governance shading language hosted by Khronos that simplifies graphics development across platforms. Designed to tackle the growing complexity of shader code, Slang offers modern programming constructs while maintaining top performance on current GPUs.

See Session Details

Tuesday, July 21
12–1:30 p.m. PT
Concourse Hall

Learn to build GPU ML inference pipelines with Slang. Use a lightweight, open set of pre-written kernels to implement an MNIST CNN from scratch: load SafeTensors weights, run inference, and apply kernel fusion for better performance. Hands-on, cross-platform, and highly customizable—ideal for games, tools, and research.

See Session Details

Wednesday, July 22
9–10:30 a.m. PT
NVIDIA Lab Room, Room 502B

Welcome to the first course in the NVIDIA Physical AI Agent Bootcamp.

Physical AI systems need visual worlds that can be rendered, inspected, queried, and trusted before they are used for simulation, robotics testing, or training. This hands-on course introduces that foundation by guiding attendees through building an OpenUSD-based RTX™ viewport with NVIDIA Omniverse™ libraries and AI-agent-assisted development.

Starting from a minimal Python renderer, attendees will create an interactive app that loads USD scenes, displays RTX output, exposes camera views, queries scene attributes, and writes image results. They will also learn a repeatable agent workflow: Define the goal, provide context, name the relevant skills, review the generated diff, and run only after the code is understood.

By the end, participants will have a working RTX viewport application and a practical method for using AI agents to build reliable graphics and simulation tools for physical AI workflows.

See Session Details

Wednesday, July 22
10:15–11:45 a.m. PT
Concourse Hall

Hands-on course on Newton, a GPU-accelerated physics engine, and its integration with Isaac™ Lab for robot learning. Covers Newton’s architecture and import pipeline, solver and contact tuning, articulation and sensors, then training and evaluating policies in Isaac Lab with Newton as the physics backend.

See Session Details

Wednesday, July 22
10:45 a.m.–12:15 p.m. PT
NVIDIA Lab Room, Room 502B

Physics is at the heart of building reliable physical AI systems, and this course in the NVIDIA Physical AI Agent Bootcamp explores how to move from visual inspection into simulation readiness.

Workflows in physical AI need assets that are structured, validated, and physically meaningful. Building on the prior OpenUSD and RTX viewport lab, this hands-on course moves from visual inspection into simulation readiness.

Attendees will validate OpenUSD assets for simulation-ready (SimReady) workflows, convert CAD and Gaussian splat content to USD, create a physics stage, and assemble environments such as stairs, ramps, or other test layouts. They will enable physics, make scene objects interactable, and run simulations to see how assets behave under gravity and user input.

By the end, attendees will have a runnable physics scene with validated assets, converted USD content, and an interactive environment ready for robotics testing or physical AI workflows.

See Session Details

Wednesday, July 22
12–1:30 p.m. PT
Concourse Hall

Hands-on course on preparing robot USD assets for simulation, covering why physics tuning is foundational to robot learning, inspecting and configuring colliders and joints with OpenUSD/PhysX™, and tuning control gains for stable, realistic motion. Participants work with a robot hand asset and apply best practices for simulation-ready authoring.

See Session Details

Wednesday, July 22
1:45–3:15 p.m. PT
NVIDIA Lab Room, Room 502B

Blender is where many 3D ideas first take shape, and this course in the NVIDIA Physical AI Agent Bootcamp shows how to extend that familiar workspace with Omniverse libraries instead of moving the work somewhere else. Attendees will use AI agents to scaffold a Blender integration that connects ovrtx, ovphysx, and ovstage into a live creative workflow.

The session walks through bringing GPU-accelerated path-traced rendering into Blender’s viewport. Along the way, attendees will see how Blender’s scene graph can connect to Omniverse-powered rendering and simulation services.

By the end, participants will have an RTX-rendered, physics-enabled scene running inside Blender, plus a clearer model for how composable Omniverse libraries can extend existing tools used by artists, technical directors, and simulation teams.

See Session Details

Wednesday, July 22
3:30–5 p.m. PT
NVIDIA Lab Room, Room 502B

This hands-on course in the NVIDIA Physical AI Agent Bootcamp turns an empty USD stage into a working Isaac Sim™ robot scene, with AI agents acting as simulation setup partners. Attendees will import a robot manipulator from URDF, compose the scene using prior lab assets or user-selected environments, and bring SimReady content into Isaac for testing.

The session focuses on the practical path from “nothing is in the scene” to “the robot picked up the cube.” Participants will configure the robot, prepare the object, validate physics behavior, tune the scene, and execute a basic pick-and-place task. Agent skills handle repeatable setup steps so attendees can focus on scene intent, simulation checks, and task behavior.

By the end, attendees will have a composed Isaac Sim scene with a physics-validated robot, interactive assets, and a successful pick-and-place task that connects OpenUSD scene building to robotics simulation.

See Session Details

Thursday, July 23
10:15–11:45 a.m. PT
Concourse Hall

We introduce a novel capture-to-simulation pipeline for in-the-wild 3D Gaussian Splat scenes, showing our research-based solutions for segmenting objects, predicting their volumetric mechanical properties using a recent learning-based method, and mixed splat-mesh physics simulations, all supported by recent features in the Kaolin Library.

See Session Details

Thursday, July 23
12–1:30 p.m. PT
Concourse Hall

Learn how to reconstruct a large scene for robotics testing using NVIDIA Omniverse NuRec Gaussian-based reconstruction technologies to perform multi-GPU training, object segmentation, and extraction. This lab will walk through core concepts with a step-by-step workflow for data capture, reconstruction, and object level-integration for robotics simulation in NVIDIA Isaac Lab.

NVIDIA at SIGGRAPH 2026

NVIDIA Keynote

Announcements

NVIDIA Puts AI Agents to Work Building Simulation-Ready 3D Worlds

AI Agents Expand Creative Tools to Millions

NVIDIA AI for Media Helps Newsrooms Detect Synthetic Video

Now Openly Available, NVIDIA Cosmos 3 Edge for Local Physical AI

NVIDIA NemoClaw on DGX Station Brings Secure, Specialized AI to Deskside Computers

NVIDIA Research Brings Computer Graphics Into Real-Time Systems for World Generation and Physical AI

Special Events

Physical AI Day

RTX Rendering Day

AI In Production Day

Educators' Day

Schedule at a Glance

Physical AI Day

RTX Rendering Day

AI in Production Day

Stream Demos From SIGGRAPH

NVIDIA Hands-On Labs

Nsight Graphics in Action: Develop and Debug Modern Ray-Tracing Applications

NVIDIA Graphics Developer Tools Road Map: Agentic AI and Beyond

AI-Assisted Graphics Debugging with Nsight Graphics

AI-Assisted Graphics Profiling with Nsight Systems

From Perception to Prediction—Developing Physical AI With Cosmos 3

Introduction to Slang: The Next-Generation Shading Language

Hands-On Machine Learning with Slang: Building High-Performance GPU Inference Pipelines

Ray Trace Your Way To A Better Life with Omniverse Libraries, OpenUSD, Agents, and You

Accelerate Robot Learning With NVIDIA Isaac Lab and Newton

SimReady or Not, Here Comes Gravity with OpenUSD for Simulation

Simulating a Dextrous Hand For Robotics With OpenUSD

Blender, Oranges, and OVRTX (Not Your Typical Smoothie)

Isaac Sim and the Fine Art of Making Your Robot Pick Things Up

From 3D Captures to Simulated Digital Environments

Advancing World Simulation With 3D Gaussian Splatting for Large-Scale Environment Reconstruction

NVIDIA Research Presentations at SIGGRAPH

8DNA: 8D Neural Asset Light Transport by Distribution Learning

ADS: Random Sampling of Occupancy Functions Using Adaptive Delaunay Scaffolding

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models

DJM: Compact Base Meshes for Displacement Mapping using Triangle Jacobians

A Generalizable Light Transport 3D Embedding for Global Illumination

GPC: Large-Scale Generative Pretraining for Transferable Motor Control

Toward Richer Material Generation via Procedural Data Enhancement

Mixed Material Point Methods for Stiff Elastoplasticity

MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives

NILE: Nesting Interleaving of Low-Dimensional Elements

PureSample: Neural Materials Learned by Sampling Microgeometry

RCGP: Resource Contracts for Graphics Programming

Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion

Real-time Level-of-Detail Rendering with ReSTIR

Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation

SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control

Spatio-Temporal Control Variates with ReSTIR for Real-Time Rendering

Taming optimization variance in compact neural shading networks

TSMC: Time-varying Scene Mesh Compression

VideoNeuMat: Neural Material Extraction from Generative Video Models

Don’t Miss Our Partners at SIGGRAPH

NVIDIA Programs

NVIDIA Research

NVIDIA Deep Learning Institute (DLI) Teaching Kit Program

Access Tools, Learning Resources, and Forums

NVIDIA RTX Spark™—A New Beginning

NVIDIA Studio: Built for Creators, Designed to Inspire

NVIDIA RTX Spark™—A New Beginning

Startups—Start Here

NVIDIA RTX PRO Blackwell

Like No Place You’ve Ever Worked

Sign up to be notified about NVIDIA at SIGGRAPH 2026