New paper with Yann LeCun asks: can a JEPA learn a latent map of the world?
mengyer · x · 2026-11-20
A new paper from a team including Yann LeCun, Yilun Kuang, and yingwww explores whether a JEPA (joint-embedding predictive architecture) can learn a latent map of the world — an empirical test of LeCun's long-argued world-model path, released alongside a discussion thread.
More from Research
- seq2fun assumes fixed cell state; transcriptome-only virtual cell models ignore DNA regulation — anshulkundaje · 2026-11-20
- Paper Revisits How Longshoremen Unions Faced the Containerization Shock — Afinetheorem · 2026-11-20
- All-star research group releases timely review of rapidly accelerating AI science field — anshulkundaje · 2026-11-20
- Stanford-Led Team Releases Review on Deep Learning for Gene Regulation — anshulkundaje · 2026-11-20
- AI Proves Optimal Solutions to MIPLIB Open Problems Unsolved for 9 Years — IgorCarron · 2026-11-20
- Yao Shunyu's private talk notes leak: small-model hierarchies, RSI, small-experiment traps — yangyi · 2026-11-20