arXiv (All)
open access
Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models
Latent world models learn to predict observed transitions, yet low prediction error alone does not guarantee reliable planning. Inspired by self tickling experiments in neuroscience showing that disrupting motor sensory correspondence increases prediction mismatch, we examine whether learned world m
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models#1201563
- Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning#926474
- VIScore: Diagnosing Planning-Relevant Quality in Latent World Models#972347
- ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning#1131175
- BadWAM: When World-Action Models Dream Right but Act Wrong#1049924
Record · ID 1200190
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive