Efficient and Adaptive Human Activity Recognition via LLM Backbones

ArXi:2605.12019v1 Announce Type: cross Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while remaining robust to heterogeneous and evolving deployment conditions. Recent advances based on Transformer architectures have significantly improved recognition performance, but typically rely on task-specific models trained from scratch, resulting in high