From-scratch NumPy MLPs for MNIST, plus a larger teacher–student setup that demonstrates subliminal learning (implementing Cloud et al. (2025)).
-
Updated
Sep 28, 2025 - Jupyter Notebook
From-scratch NumPy MLPs for MNIST, plus a larger teacher–student setup that demonstrates subliminal learning (implementing Cloud et al. (2025)).
From MNIST noise distillation to Llama-3.1-70B: subliminal learning, token entanglement, causal state transfer, and multi-token confounds.
Replicating latent-space backdoor leakage and behavioral transfer in LLMs using Pythia-70M.
Code to reproduce the results of the paper "Learning Through Noise: Why Subliminal Learning Works and When It Fails"
Artifact-backed experiments on the behavioral half-life of subliminal traits under recursive self-distillation.
Add a description, image, and links to the subliminal-learning topic page so that developers can more easily learn about it.
To associate your repository with the subliminal-learning topic, visit your repo's landing page and select "manage topics."