arXiv (All)
open access
Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights
We show that neural network weights can be explicilty fintuned to admit a smaller grammar. Weight Pair Encoding (WeightPE) does so by placing a lossy Re-Pair compressor inside a straight-through estimator. The int8 weights of the network are flattened into one string, and near-matching Re-Pair patte
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
- ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography#141425
- How Weight Encoding Affects Language Model Placement and Performance on the Apple Neural Engine#1076127
- Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures#1110571
- Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures#919271
- Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis#467130
Record · ID 1106263
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