arXiv (All)
open access
How Shared Representations Become Specialized: Formation, Maintenance, and Latent Susceptibility
When several predictions use the same internal representation, information about some targets can remain easier to recover than information about others. We study how this specialization forms, persists, and changes in minimal artificial learners. With reconstruction errors weighted equally during l
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
- Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures#1186658
- Complete or Sparse: A Tale of Two Identifiabilities#1356187
- Loss-Invariant Projections as Passive Probes of Learned Representations#1202614
- Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations#1217641
- Tracking the Fidelity of Internal Neural Representations with Error-In-Variables Regression#627783
Record · ID 1327080
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