Edge AI hardware has never been more capable, yet shipping computer vision and physical AI products still takes months longer than it should. From our work at Ultralytics integrating models with hardware vendor SDKs across many platforms, we’ve learned that […]

In medical settings, IV infusions deliver intravenous fluids or medications by allowing fluid to flow from an IV bag through tubing and a drip chamber, known as an administration set. In this talk, we will show how SAFEflow uses embedded […]

The next generation of AI agents is moving beyond cloud-based text-only models and will interact with the physical multimodal world in real time. In the vision domain, AI agents rely on vision-language models (VLMs) as their backbones. However, deploying massive […]

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 […]

The AI landscape has long been dominated by the “bigger is better” paradigm, but a significant shift is underway. Small language models (SLMs), generally defined as models with fewer than 10B parameters, are emerging as powerful, efficient and practical alternatives […]

Most vision AI systems that work in the lab fail when deployed across hundreds of real-world locations. At Intuitivo, we operate 2,000+ autonomous points of purchase across enterprise locations, including Tesla, Microsoft, Walmart and Bank of America facilities, processing over […]

Consumer LiDAR scanning is easy; converting noisy, incomplete phone scans into engineering-grade building models is not. In this talk, we share what we learned converting 150M+ square feet of iPhone/iPad scans into clean, structured geometry with semantic labels. We’ll break […]