Chhabra introduces RLNF, training AI models on brain-signal preferences
Article timeline
The articles in this story. Times are ET.
Rohan PaulXRohan Paul shares RL with Neural Feedback for training image models on brain signalsAIRohan Paul shares a post introducing RL with Neural Feedback (RLNF), which trains AI models to respond to human preferences using brain signals. The post says an image model adjusts a face toward what the viewer finds more attractive, without ratings, clicks or prompts. An attached chart, citing Arshamian et al. 2022, shows how personal preferences are across landscape scenes, faces, odours, voices and abstract art.
elvisXResearchers train AI models on preferences decoded from brain signalsAIThe researchers introduce reinforcement learning with neural feedback (RLNF), which trains AI models to respond to human preferences using brain signals alone. A demonstration shows a face that transforms into a version the viewer finds more attractive, based on their neural responses. The poster says the approach could combine reinforcement learning, brain-computer interfaces and agents to enable personal intelligence at scale.
