LeCun Debates Whether LLM Weights Hold Knowledge as JEPA Gains Proof

Yann LeCun cited a new paper as proof that JEPA world models can achieve understanding with far fewer parameters than LLMs, which he argues rely on stockpiling declarative knowledge — sparking debate with scholars who contend LLM weights do encode a form of understanding.

2026-11-04 ~ 2026-11-05 · 2 related posts

• LeCun says he 'brought a proof': JEPA world models can match LLMs with far less memory — ylecun · 2026-11-04
• LeCun vs. researcher: LLM weights store no discrete facts — JEPA bets on 'understanding' instead — solyarisoftware · 2026-11-05