Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference
Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation. Language models have exhibited a similar capacity for adaptive "reasoning." However, transferring this capability to continuous control policies has been challenging, as directly reasoning in language space may lack the granularity for spatial understanding and precise motions. In this work, we show that reasoning for control policies can emerge by organizing information in an autoregressive latent space reminiscent of a memory palace, where retrieval is iterative and adaptive. O
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%modelplaneai/modelplane →
- PossiblePossibly related (embedding) · 51%sandst1/remind →
- PossiblePossibly related (embedding) · 50%GuyMannDude/mnemo-cortex →
- LinkedLinked via arxiv author · 85%Chuning Zhu →
“Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference”
- LinkedLinked via arxiv author · 85%Eva Xu →
“Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference”
- LinkedLinked via arxiv author · 85%Jose Barreiros →
“Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference”
- LinkedLinked via arxiv author · 85%Krishnan Srinivasan →
“Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference”
- LinkedLinked via arxiv author · 85%Paarth Shah →
“Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference”