New paper proposes epiplexity, an unsupervised objective for learnable novelty
MacrinePhD · x · 2026-07-22
A new paper, Intelligence from Learnable Novelty, argues for an unsupervised AI objective called epiplexity.
- The core idea is to make models pursue only surprises they can actually learn from.
- The paper is presented as a simple mathematical rule that could help AI automatically organize data, discover complex patterns, and solve games without supervision.
- The post frames it as a potentially big deal for AI because it links novelty, learning, and complex-systems behavior in one objective.
- Authors mentioned in the post are @YanboZhang3 and @drmichaellevin.
Related event: New Paper Unifies Intelligence Concepts via Learnable Novelty(7 posts)→
More from Research
- UK AISI: under $80 of fine-tuning fully restores filtered bio capabilities in open-weight models — connoraxiotes · 2026-10-27
- RFD4-Proteina runs on an RTX 3060: protein design from $0.001 per design — AllThingsApx · 2026-10-27
- University of Freiburg's Generative Intelligence Lab recruiting funded PhDs via ELLIS, apply by Oct 31 — yuyinzhou_cs · 2026-10-27
- Nature Physics: reprogrammable refractive index enables arbitrary multimode wave control for ML — MarioKrenn6240 · 2026-10-27
- Wakaru open-sources ontologize: labeling datasets from model activations — amplifiedamp · 2026-10-27
- EMNLP Oral paper traces multilingual representations in LLMs with cross-layer transcoders — ZhijingJin · 2026-10-27