• Monday | October 27, 2025 | 8:30 - 9:30

    Artificial Intelligence (AI) applications have entered and impacted our lives unlike any other technology advance from the recent past. While current AI tools are approaching Artificial General Intelligence (AGI) capabilities, large gaps persist due to diminished benefits despite deploying enormous computing and ever-increasing energy demands. This quandary requires a holistic approach in determining energy efficient solutions for achieving AGI. While the holy grail for judging the quality of an AI model has largely been serving accuracy, and only recently its resource usage, neither of these metrics translate directly to energy efficiency, latency, or mobile device battery lifetime. More recently, generative AI relying on transformer, diffusion, or state-space models have revolutionized the way we approach reasoning and learning tasks across all types of modalities, from image to video and language, bringing increased performance at the expense of significant hardware costs. This talk uncovers the need for building accurate, platform‐specific power and latency models and efficient hardware-aware design methodologies for AI systems, thus allowing AI and hardware designers to identify not just the best accuracy AI configuration, but also those that satisfy given hardware constraints. Furthermore, together with model compression techniques, such as quantization and sparsity-aware co-design, these approaches demonstrate the feasibility of achieving cloud to edge energy efficient generative AI for multi-modal tasks.

  • Tuesday | October 28, 2025 | 8:00 - 9:00

    Higher levels of automation in road transport mobility are a true moonshot. Very few OEMs have so far successfully obtained road approval for their Level 3 automated driving system, BMW being one of them. AI already now is a major technological driving force behind automated driving and will continue to be. We will highlight current frontiers of AI development in safety relevant systems and explore, how expected evolution of the technology will influence the road ahead for automated driving functions. Growth in sensor data volume and machine learning compute demand is fuelling a race to ever more potent embedded systems. Just brute-forcing hardware will not do. Innovative semiconductor solutions such as chiplets come to the rescue. As does intelligent hardware-software-co-design.

  • Wednesday | October 29, 2025 | 8:00 - 9:00

    Modern computing workloads, from  generative AI, to digital twins, to fully homomorphic encryption, require sustained energy efficiency improvements, which cannot be matched simply by technology evolution. To tackle the challenge, we need  to aggressively optimize computing platforms leveraging specialization across all levels of the design hierarchy, pushing into domain-specific design automation tools and methodologies.  In this talk, I will give concrete examples of deep domain specialization, emphasizing  the strategic importance of an end-to-end (models,software, instruction set architecture, digital IPs, EDA tools) open-platform approach to achieve the ultimate efficiency, while promoting a healthy innovation ecosystem.