arXiv Machine Learning August 4, 2026 By Sahil Rajesh Dhayalkar

Kilobyte Models: Neural Networks as a Seed and a Quantized Latent

Read the original on arXiv Machine Learning →

arXiv:2608. 00860v1 Announce Type: new Abstract: The cost of storing and transmitting a trained neural network scales with its parameter count, a bottleneck for over-the-air updates, on-device libraries, and other bandwidth-bound deployments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 10

SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

arXiv:2510.08999v2 Announce Type: replace-cross Abstract: Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight...

By Ziyi Wang, Nan Jiang, Guang Lin, Qifan Song

efficiency

arXiv AI

Sep 2

A Mathematical Theory of Reusable Neural Bases for Network Compression

The paper introduces the Linear Reusable Neural Bases Architecture (LRNBA), a framework that represents each network block as a linear combination of shared neural bases to improve parameter efficiency and reduce memory cost. Inspired by recurrent neural network designs, LRNBA enables the construction of wider and deeper networks within the same parameter budget. Experiments show that models using LRNBA converge as fast or faster than classical architectures, achieve lower loss, and maintain stable training dynamics.

By Binshuai Wang

arXiv Machine Learning

Jul 14

Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

arXiv:2607. 11883v1 Announce Type: new Abstract: Compression is fundamental to intelligence.

By Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang, Andrew Gordon Wilson

llms efficiency benchmarks

arXiv Machine Learning

Jul 7

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

arXiv:2607. 02893v1 Announce Type: new Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width.

By Hamish Ogilvy

llms efficiency

Hugging Face Trending Papers

Jun 22

Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks

Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these developments, training and deployment of neural network models on embedding and edge devices face significant challenges due to limited memory and computational resources.

rag efficiency benchmarks

arXiv AI

Jun 2

Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks

arXiv:2606. 00130v1 Announce Type: cross Abstract: We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trained end-to-end by reverse-mode automatic differentiation (AD).

By Andrzej Cichocki, Michal Wietczak

One email a morning, machine-written

Related stories

SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

A Mathematical Theory of Reusable Neural Bases for Network Compression

Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks

Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks