Learning Through Noise: Why Subliminal Learning Works and When It Fails
Authors Brockers VC, Ventzke RD, Neuhaus V, Hidalgo-Ogalde B, Priesemann V Journal Arxiv Citation arXiv:2605.23645 Abstract In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input output pairs. Prior explanations tie


