arXiv (All)
open access
Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
Joint-Embedding Predictive Architectures (JEPAs) are prone to representation collapse, typically mitigated through empirical heuristics. We develop an early-training stability theory that unifies these heuristics. Linearising the coupled JEPA gradient flow around the trivial fixed point reveals two
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
- Joint Embedding with Dynamic Integration network (JEDI-net)#1342190
- I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?#1105719
- Scalar Representations of Neural Network Training Dynamics#321854
- A lift for input-convex neural net training#1062907
- ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models#1132153
Record · ID 1186658
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