Skip to main content

Real2Sim for Embodied Data Generation

abstract background

This beginner-to-intermediate workshop introduces a practical pipeline for building scalable embodied Synthetic Data generation systems for robotics and physical AI. Participants will learn how to transform real-world objects into interaction-ready simulation assets through a Real2Sim workflow focused on object-centric reconstruction, and simulation integration on AMD Instinct GPUs.

July 22, 2026 14:30 - 15:15

David Li
David Li

SMTS Product Application Engineer | AMD

Alex He
Alex He

SMTS Product Application Engineer | AMD

Topic

AI Training & Inference

Physical AI & Robotics

Session Type

Workshop

Related Product

Instinct, Radeon, ROCm, EPYC

Related Sessions

View All Sessions
  • Introduction to Robotics with ROS2 on AMD

    This intermediate, interactive session focuses on deploying an end-to-end Vision-Language-Action (VLA) pipeline using ROS 2 and multimodal models to control a robotic arm. Participants will work through the steps to build and deploy a system that responds to physical inputs with real-world actions. Prior familiarity with ROS 2 and VLA concepts is recommended.;This intermediate, interactive session focuses on deploying an end-to-end Vision-Language-Action (VLA) pipeline using ROS 2 and multimodal models to control a robotic arm. Participants will work through the steps to build and deploy a system that responds to physical inputs with real-world actions. Prior familiarity with ROS 2 and VLA concepts is recommended.

    July 23, 2026

  • Training at Scale with AMD Primus

    Primus makes large scale training on Instinct reliable, debuggable and highly performant. It supports the latest OSS training frameworks, models, and is expanding support to new, cutting-edge model architectures, training techniques, and datatypes. Primus’ SOTA pre and post training performance, proven at scales of thousands of GPUs, positions instinct as a competitive solution for model development at frontier labs, enterprises and AI startups.;Primus makes large scale training on Instinct reliable, debuggable and highly performant. It supports the latest OSS training frameworks, models, and is expanding support to new, cutting-edge model architectures, training techniques, and datatypes. Primus’ SOTA pre and post training performance, proven at scales of thousands of GPUs, positions instinct as a competitive solution for model development at frontier labs, enterprises and AI startups.

    July 23, 2026

  • Benchmarking AI Systems: from Model Metrics to Real-World Performance

    The agentic AI stack has evolved to fast multi-model orchestration, tool-augmented reasoning, and long-running inference chains. The hardware conversation hasn't kept up, and many teams default to one GPU vendor without evaluating alternatives. This interactive session is for builders to learn what they're missing. We'll review head-to-head benchmark data from third-party testing, discuss production-ready serving stacks on ROCm, and break down TCO for teams running multi-step agents at scale.;The agentic AI stack has evolved to fast multi-model orchestration, tool-augmented reasoning, and long-running inference chains. The hardware conversation hasn't kept up, and many teams default to one GPU vendor without evaluating alternatives. This interactive session is for builders to learn what they're missing. We'll review head-to-head benchmark data from third-party testing, discuss production-ready serving stacks on ROCm, and break down TCO for teams running multi-step agents at scale.

    July 23, 2026

  • Agentic Kernel Performance Tuning with AMD ROCm

    This session introduces an agentic kernel development workflow for optimizing AI and HPC workloads on AMD ROCm. Learn how a self-directing optimization loop can profile, analyze, optimize, validate, and generate production-ready kernel improvements with minimal manual tuning. The talk highlights how AMD is accelerating kernel engineering by reducing weeks of performance optimization effort into an automated, scalable workflow for developers and performance engineers.;This session introduces an agentic kernel development workflow for optimizing AI and HPC workloads on AMD ROCm. Learn how a self-directing optimization loop can profile, analyze, optimize, validate, and generate production-ready kernel improvements with minimal manual tuning. The talk highlights how AMD is accelerating kernel engineering by reducing weeks of performance optimization effort into an automated, scalable workflow for developers and performance engineers.

    July 23, 2026

  • Efficient LLM Serving at Scale with Unified Caching

    This is an advanced user hands-on workshop to show TensorMesh and AMD enabling efficient LLM serving through an unified caching layer. You will learn how tiered KV cache management can brings out the benefits of cache-aware inference, improving throughput under interactive latency SLAs, reducing TTFT through KV cache reuse/offload & enabling production-style distributed inference on Instinct GPUs.;This is an advanced user hands-on workshop to show TensorMesh and AMD enabling efficient LLM serving through an unified caching layer. You will learn how tiered KV cache management can brings out the benefits of cache-aware inference, improving throughput under interactive latency SLAs, reducing TTFT through KV cache reuse/offload & enabling production-style distributed inference on Instinct GPUs.

    July 23, 2026

  • Power is Your Biggest Hidden Cost: How AMD Can Help

    Power is the AI infrastructure cost nobody budgets for until it breaks the business case. In this interactive technical session, an expert from 5C joins AMD to unpack how power consumption impacts total cost of ownership across inference and training deployments. Discuss how intelligent power management, real-world thermal constraints, and silicon-level efficiency shape what your AI infrastructure can sustain. Practical insight for architects and operators making deployment decisions today.;Power is the AI infrastructure cost nobody budgets for until it breaks the business case. In this interactive technical session, an expert from 5C joins AMD to unpack how power consumption impacts total cost of ownership across inference and training deployments. Discuss how intelligent power management, real-world thermal constraints, and silicon-level efficiency shape what your AI infrastructure can sustain. Practical insight for architects and operators making deployment decisions today.

    July 23, 2026

  • Accelerating LLM Inference on AMD ROCm with AITER and ATOM

    This technical talk introduces AITER and ATOM, optimized inference technologies for AMD ROCm software. Learn how AITER accelerates LLM and MoE execution with optimized kernels and distributed inference enhancements, while ATOM integrates these capabilities into familiar vLLM and SGLang workflows through plugin-based acceleration. The session highlights how AMD enables scalable, high-performance open-source LLM serving while preserving existing developer and deployment workflows.;This technical talk introduces AITER and ATOM, optimized inference technologies for AMD ROCm software. Learn how AITER accelerates LLM and MoE execution with optimized kernels and distributed inference enhancements, while ATOM integrates these capabilities into familiar vLLM and SGLang workflows through plugin-based acceleration. The session highlights how AMD enables scalable, high-performance open-source LLM serving while preserving existing developer and deployment workflows.

    July 23, 2026

  • Tool Calling Robots: Agentic Workflows Complementing Physical AI

    Robots with tool calling capabilities expose coarse- and fine-grained control as software APIs. A robot with access to these APIs can then reason over what it sees, adjusting cameras, checking for humans, or sequencing actions – all before any motion executes. Join us for an interactive discussion to have all your questions answered on how this agentic layer, running on capable edge hardware, can greatly amplify the emerging benefits of physical AI.;Robots with tool calling capabilities expose coarse- and fine-grained control as software APIs. A robot with access to these APIs can then reason over what it sees, adjusting cameras, checking for humans, or sequencing actions – all before any motion executes. Join us for an interactive discussion to have all your questions answered on how this agentic layer, running on capable edge hardware, can greatly amplify the emerging benefits of physical AI.

    July 23, 2026