RLNF: AI image models trained on brain signals morph faces to your taste in real time
rohanpaul_ai · x · 2026-10-31
- Researchers introduce RL with Neural Feedback (RLNF): training AI image models on brain signals alone, with no ratings, clicks, or prompts from the user.
- Demo: a face image self-transforms into a more attractive version for the subject while they are looking at it, optimizing a decoded preference signal in real time.
- An accompanying chart shows how personal taste is across domains: landscape scenes are only 28% personal, faces 43%, odours 59%, voices 66%, and abstract art 74% — the more abstract the aesthetic, the more personal, which is exactly what neural feedback can capture that explicit ratings cannot.
Related event: RLNF Trains AI Models on Human Preferences Using Brain Signals Alone(6 posts)→
More from Multimodal
- NVIDIA open-sources NemotronLabs RE-USE, a 9.6M-param multilingual speech denoiser — NVIDIAAI · 2026-10-31
- AI-generated fake trailer imagines a 1999 Dino Crisis movie with retro VHS feel — noizlab_studio · 2026-10-31
- Spatial Hub aggregates ~5000 public COLMAP-compatible spatial datasets for world models — janusch_patas · 2026-10-31
- Single image to walkable 3D Gaussian splat scene using World Labs Atlas and WebGPU — XRarchitect · 2026-10-31
- AI video reimagines Suicide Squad's Joker as a rapper in a full music-video treatment — Silver_War5476 · 2026-10-31
- 60+ community-made ChatGPT slash-style words turn one word into a full visual style — heyshrutimishra · 2026-10-31