Meta Researcher Proposes CAPI, a New Self-Supervised Learning Method for Masked Image Modeling
iScienceLuvr · x · 2026-07-28
Meta researcher Tim Darcet, known for DINOv2, has proposed a new self-supervised learning method called CAPI (Cluster and Predict Latent Patches) to improve masked image modeling. The paper will be presented at MedARC Journal Club on July 30. MedARC believes CAPI could advance medical imaging foundation models beyond DINO and MAE paradigms.
More from Research
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- Nature Comment: Provenance, not interpretability, grounds trust in autonomous science — gabepgomes · 2026-08-24
- New Architecture RHEA: Train 1B Model on 8GB VRAM — zemondza · 2026-08-24
- Trained two 16M-param models to do generative CAD with real physics — debreuil · 2026-08-24
- Claude model helps discover complex structure on S^6, solving 60-year-old math problem — Singularitarian · 2026-08-24
- Study: Agents read instructions/notes 60.5% of the time, rarely touch API docs — dair_ai · 2026-08-24