Fucheng Han
YOU?
Author Swipe
View article: ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training Open
Token-level attention tuning, a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT), has emerged as a promising way to improve frozen LLMs with interpretable interventions. However, …
View article: Analogue simulation and practical application effect analysis of relay protection strategy of power system in high altitude area
Analogue simulation and practical application effect analysis of relay protection strategy of power system in high altitude area Open
As a safety protection measure in power systems, relay protection can quickly and accurately determine the type of fault and its cause. In order to adapt to the increasingly complex operating environment of relay protection systems in high…