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

arXiv:2609.31564 · cs.LG · Submitted 2026-09-25 · Read on arXiv

cs.LG

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/huggingface/pytorch-image-models

Terminology

• Accuracy — 17× in this paper · explained in 1 episode
• Quantization — 8× in this paper · explained in 12 episodes
• In International Conference on Learning Representations — 5× in this paper
• Clustering — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Quantization-Aware Training — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
• Git Re-Basin: Merging Models modulo Permutation Symmetries
• Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Random Access to Grammar Compressed Strings
• DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
• Self-Compressing Neural Networks
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
• Improving Matrix-vector Multiplication via Lossless Grammar-Compressed Matrices
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• LoRA: Low-Rank Adaptation of Large Language Models
• Editing Models with Task Arithmetic
• Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
• Quantizing deep convolutional networks for efficient inference: A whitepaper
• Scalable Model Compression by Entropy Penalized Reparameterization
• TorchAO: PyTorch-Native Training-to-Serving Model Optimization
• Neural Machine Translation of Rare Words with Subword Units
• Zero-Shot Quantization via Weight-Space Arithmetic
• How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks