arXiv (All)
open access
Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs
Post-training quantizers select finite code changes using reconstruction proxies or local loss approximations, but the utility of a quantization move depends on the state through which it is executed. We identify two sources of this contextual dependence. First, the displacement of the move matters:
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
- MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs#187231
- Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding#926093
- Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss#128274
- APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images#818712
- APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images#808720
Record · ID 996683
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