Unverified50% confidenceFactExact time
In recent years the term world model has been borrowed by the generative AI field to refer to models capable of generating interactive, explorable three-dimensional dynamic environments, with representative work including Google DeepMind's Genie series, OpenAI's Sora (partly regarded as a prototype of a world simulator), and various playable video generation studies.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
Unverified世界模型是指能够根据用户输入动态生成、预测并渲染连贯虚拟环境的AI系统，其核心价值在于可交互性与时序一致性75% similarUnverifiedMeta's research team's V-JEPA model, Google DeepMind's Genie, and other projects are exploring ways to enable AI to build an internal simulation of the physical world.74% similarUnverifiedOpenAI claimed in the Sora technical report that the model demonstrates an understanding of 3D consistency, object permanence, and long-term temporal coherence, proposing that Sora is a prototype of a "world simulator."72% similarVerifiedTool-Augmented AI is an important development direction for current large model applications, with mechanisms such as OpenAI's Function Calling and Anthropic's Tool Use underpinning this paradigm at the foundational level.71% similarUnverifiedArtificial Analysis平台覆盖OpenAI、Anthropic、Google、Meta、Mistral以及智谱AI、DeepSeek等数十家模型提供商的产品71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1104318API
curl https://kongchang.com/api/v1/knowledge/claims/1104318MCP
get_claim(id=1104318)