AI RESEARCH
Gravity-Aware Hierarchical Routing for Lightweight SensorLLM on Human Activity Recognition
arXiv CS.AI
•
ArXi:2606.04019v1 Announce Type: cross Recent studies on sensor-language alignment have shown that two-stage frameworks can improve the semantic modeling ability of wearable-sensor human activity recognition (HAR), where SensorLLM-style methods first perform motion-to-language alignment and then fine-tune the model for downstream tasks. However, our experiments reveal a consistent failure mode when the