Chao Huang

Compiling mobile GUI navigation into deterministic commands turns slow, multi-turn VLM visual search into sub-second execution at zero token cost without sacrificing open-ended task completion.

Inspired by recent findings that self-attention acts as a low-pass filter and that its low-frequency components are informative, AttnPrint for white-box provenance is developed, which achieves strong derivative-model detection performance while remaining robust to five downstream modification techniques.