ADNTNs compress DNN weights by 2000x-77000x per layer on AlexNet and VGG-16 using nonlinear tensor network cores trained with reverse-mode AD, often matching or exceeding baseline accuracy.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MixT compresses Transformer LLMs by substituting targeted linear projections with tensor-operator mixtures, preserving MMLU accuracy up to model-specific boundaries where parameter count drops 47.5% and inference memory 60.4% on LLaMA2-7B.
citing papers explorer
-
Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks
ADNTNs compress DNN weights by 2000x-77000x per layer on AlexNet and VGG-16 using nonlinear tensor network cores trained with reverse-mode AD, often matching or exceeding baseline accuracy.
-
A general tensor-structured compression scheme for efficient large language models
MixT compresses Transformer LLMs by substituting targeted linear projections with tensor-operator mixtures, preserving MMLU accuracy up to model-specific boundaries where parameter count drops 47.5% and inference memory 60.4% on LLaMA2-7B.