Unverified50% confidenceFactExact time
Dreamer系列（Hafner等人，2019-2023）核心是循环状态空间模型（RSSM），通过重构观测学习表征，属于生成式方法
1
Sources
50%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
Related Claims
UnverifiedDreamerV3采用的RSSM（循环状态空间模型）由Danijar Hafner等人提出，将隐状态分解为确定性循环状态和随机隐变量80% similarUnverifiedDreamerV3 是基于隐空间的世界模型，在压缩的潜在表示空间中进行预测，计算效率更高63% similarUnverified近年涌现出混合专家模型（MoE，如 Mixtral）、状态空间模型（SSM，如 Mamba）、线性注意力变体等新兴架构63% similarUnverifiedThe hallucination phenomenon in large models is rooted in the autoregressive generation mechanism of Transformers, where the model learns probability distributions through the Next Token Prediction task during the pre-training phase.61% similarUnverifiedThe essence of model hallucination is probabilistic completion by the model outside the distribution of training data; core methods for reducing hallucination include providing contextual anchors, requiring the model to explicitly cite sources, and combining RAG to provide factual grounding.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/697009API
curl https://kongchang.com/api/v1/knowledge/claims/697009MCP
get_claim(id=697009)