arXiv (All)
open access
Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models
Joint-Embedding Predictive Architectures (JEPAs) learn compact latent world models by predicting future embeddings, but no single coordinate of the latent is designated to encode task progression. We carve the JEPA latent into two orthogonal subspaces with disjoint roles: a low-dimensional progressi
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
- Orthogonal JEPA: Factorized Predictive States for Latent World Models#1052275
- Flow-JEPA: Flow Matching for Robust Latent Dynamics in JEPA World Models#793253
- Flow-JEPA: Flow Matching for Robust Latent Dynamics in JEPA World Models#789249
- Mask-Aware Execution for Efficient JEPA Training#1037357
- Mask-Aware Execution for Efficient JEPA Training#1028673
Record · ID 1011117
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