arXiv (All)
open access
Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers
Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclear. Neural redundancy is typically characterized by component importance or representational similarity, both indirect proxies. We view redundancy as an input-conditioned, dynamic relation: intermediat
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
- Disentangling Representation Evolution in Transformers through Directional Decomposition#1110000
- Official Review · ICLR 2025#787185
- The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation#1155358
- Neural collapse is globally optimal in deep regularized ResNets and transformers#1000828
- The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections#1048761
Record · ID 1144226
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