Tag
A tweet discussing RL with Neural Feedback (RLNF), where a viewer's brain arousal signals are scored via embedding plus k-NN and used directly as the RL reward for personalized image generation, framed as a natural evolution beyond RLHF's click-based preferences.
Introducing RL with Neural Feedback (RLNF), a method claiming reliable training of AI models to align with human preferences using only brain signals, demonstrated via a face image that self-transforms into a more attractive version for the viewer.