Most edge vision deployments fail not because of model architecture, but because real-world training data is structurally incomplete. Sampled data can’t cover combinatorial edge cases, forcing perpetual retraining cycles that break embedded deployment, explainability requirements and silicon viability. In this […]

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 […]

This session explores practical strategies for deploying computer vision AI on far-edge devices under strict resource constraints. While highlighting FPGA-specific strengths, such as customizable dataflows, fine-grained quantization control and efficient near-sensor processing, we will also cover techniques applicable across edge […]

Vision-focused edge AI, where CNNs ruled, was compute-bound. However, today’s vision-language models (VLMs) have flipped the script: they feature as many as 70B parameters and 200K+ token contexts and are highly memory-bound, shifting the bottleneck from compute to memory. KV […]

Running computer vision on microcontrollers is becoming practical thanks to MCUs that integrate NPUs, enabling low-latency inference with tight power and cost budgets. In this session, Roboflow Co-Founder and CEO Joseph Nelson will walk through an end-to-end workflow for building […]

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 […]