arXiv (All)
open access
Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components
Task Vectors (TVs) provide a compact way to steer large language models, but they are typically treated as atomized directions merely extracted from hidden states, leaving their internal functional structure poorly understood. Motivated by prior work that decomposes in-context learning into Task Rec
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
- Beyond Reconstruction Error: Analytical and Data-Driven Action Tokenization for Autoregressive Vision-Language-Action Models#1061448
- Rules Amortize, Pairings Don't: Linguistic Structure Determines What Latent Task Representations Can Replace In-Context Learning#1155461
- Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models#1129542
- TS-SP: Learning Speaker-Preserving Representations in Audio Large Language Models#1200538
- Studying the Effects of Task Diversity Using Small Mathematical Worlds#1298246
Record · ID 1535066
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