Self-compression is a quantization-aware training technique to reduce neural network size and optimize performance for edge inference. By learning optimal bit depths for weights and activations during training, self-compression achieves significant reductions in memory footprint and bandwidth consumption while maintaining […]
In this presentation, we provide a practical end-to-end overview of the AMD Vitis AI workflow for deploying deep learning models on AMD adaptive SoCs for embedded and edge systems. These platforms are well suited for tasks like object detection and […]
In this talk, we’ll explore the evolution and implementation of multimodal generative AI at the edge targeting physical AI applications, including autonomous vehicles and humanoid robots. We’ll outline the challenges and trade-offs for implementing multimodal generative AI on resource-constrained systems […]
Traditional computer vision excels at answering “what is in the image,” but many real systems need “what is happening” and “what will happen next.” World models address this by maintaining an internal, temporally consistent representation of the environment and using […]
Battery-powered wireless vision sensors can reduce installation cost and enable deployments where external power is impractical. But once we add edge AI for on-device image processing—both to protect privacy and to minimize bandwidth—the power budget becomes the central design constraint […]
Designing a camera system requires a deep understanding of the fundamental principles of image formation and the physical characteristics of its components. Translating computer vision-based system requirements into camera system parameters is a crucial step. In this talk, we will […]
Discover how AMD’s ROCm software stack unlocks data center-class ML performance on embedded integrated GPUs, enabling diverse AI workloads from CNNs and transformers to VLMs and LLMs in power-constrained edge environments. In this technical session, we show how ROCm, HIP […]
Training a model is a crucial step in machine learning, but it can be overwhelming for beginners. In this talk, we provide a comprehensive introduction to the fundamentals of model training. We will introduce the different types of training, such […]
Successful deployment of AI on edge platforms requires system-level strategies that account for critical considerations such as latency bounds, memory behavior and orchestration of heterogeneous hardware cores. In this talk, we present techniques for running deep learning pipelines on edge […]
As generative AI models rapidly evolve—with increasingly dynamic transformer architectures and diverse framework variations—the challenge of bringing these models to the edge has grown dramatically. Traditional rule-based optimization pipelines can no longer keep pace with models whose structures shift quickly […]
Want to contact us?
Use the small blue chat widget in the lower right-hand corner of your screen, or the form linked below.
STAY CONNECTED
Follow us on X and LinkedIn.
