arXiv (All)
open access
Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs
We present Activation- and Influence-Aware Ranks (AIR), an SVD-based LLM compression framework that guides each weight matrix's low-rank approximation with a backward-signal influence metric. Starting from the activation-aware optimum of SVD-LLM(W), AIR runs a single closed-form alternating least sq
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
- GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training#1036829
- UniRank: Unified Rank Allocation for Low-Rank LLM Compression#1109083
- Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression#146922
- Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates#1078148
- Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems#370346
Record · ID 985139
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