Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control

• 类型：arxiv
• 标识：2607.26657
• 链接：https://arxiv.org/abs/2607.26657
• 主分类：multimodal
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：This work presents Enfold, which transfers this computation that constructs a future into a representation predicted from the current visual context and language instruction, and recast a world generator as a source of predictive control representations if its internal structure can be enfolded into the present.
• 待LLM分类：否
• 标题中文：Enfold：将世界模型想象折叠进预测表征以实现超高效具身控制
• TLDR中文：本文提出 Enfold，将构建未来的计算转移到由当前视觉上下文和语言指令预测出的表征中，并把世界生成器重塑为预测控制表征的来源，前提是其内部结构可被折叠（enfold）到当下。
• 来源文件：
• /inbox/tom/_candidates/2026-08-11-rag-retrieval-reranking-candidates.json
• /inbox/tom/_candidates/2026-08-11-agent-rag-longcontext-candidates.json
• [S2 enrich]