Unverified60% confidenceFactExact time
JEPA (Joint Embedding Predictive Architecture) was proposed and championed by Meta's Chief AI Scientist Yann LeCun, and is a self-supervised learning architecture.
2
Sources
60%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
LeMario：用超级马里奥训练JEPA世界模型的开源实践
Related Claims
UnverifiedJEPA is a self-supervised learning paradigm advocated by Yann LeCun and others.80% similarUnverifiedThe alternative path toward artificial general intelligence proposed by LeCun is a self-supervised learning architecture driven by a 'World Model', such as JEPA77% similarUnverifiedZhipu AI's GLM series is based on a self-developed foundational architecture, with its technical roots in the KEG Lab at Tsinghua University.67% similarUnverified该自进化架构借鉴了元学习（Meta-Learning）和神经架构搜索（NAS）领域的核心思想67% similarVerifiedThe concept of world models originates from cognitive science and reinforcement learning, strongly promoted by Yann LeCun and others, referring to an agent's internal representation of the external environment.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/556725API
curl https://kongchang.com/api/v1/knowledge/claims/556725MCP
get_claim(id=556725)