Signals 4 · free daily AI digest

Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights

Paper recorded by Signals 4 on 2026-09-25 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.LG · 机器学习 · first seen 2026-09-28

Abstract

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 patterns are made exactly equal within a global L2 budget. The network computes with the rewritten weight

Read on arXiv →

#8 most recent of 310 cs.LG papers we have recorded · ↑ newer: Uncertainty and Explainability in Deep Rough Volatility: A Neural Info · ↓ older: Generalization behavior of OPTQ and the role of regularization
Cite this page: Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights: the #8 most recent of 310 cs.LG papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/weight-pair-encoding-inducing-a-smaller-grammar-in-neural-network-weights.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions