Hydra Phase-aware characterization of LLM inference across three generations of edge SoCs ALBIREO Detector-agnostic, training-free adaptive inference for video object detection on edge GPUs RAGMark & Adaptive Edge RAG Stage-level benchmarking of retrieval-augmented generation, and compression as a runtime control knob Cross-Platform VLA Scaling How vision-language-action models scale from power-constrained edge SoCs to datacenter GPUs