🧠 Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data
💽 Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
📊 DataRater: Meta-Learned Dataset Curation
🧵 ⬇️
🧠 Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data
💽 Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
📊 DataRater: Meta-Learned Dataset Curation
🧵 ⬇️