arXiv (All)
open access
Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability
Warm-start transfer can make algorithmic tasks generalize rapidly, yet it is unclear which model components provide the gain and whether that gain remains stable under continued optimization. We study cross-operator transfer on modular arithmetic and separate efficacy (early velocity) from stability
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
- NAND Attractor Networks A Study in Subtractive Learning and Remainder-Preserving Architectures#76920
- Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs#246459
- MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems#153041
- The Identity Kernel_ Why Transmission Is Not Persistence#93562
- AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion#1116933
Record · ID 1011779
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