Cayley unitary adapters executed on real quantum hardware improve LLM perplexity by 1.4% on Llama 3.1 8B with 6000 parameters and recover 83% of compression-induced degradation on SmolLM2.
Compactifai: extreme compression of large language models using quantum-inspired tensor networks
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
A hybrid classical-quantum scheme compresses and disentangles bottleneck layers of pre-trained neural networks into MPO form for execution on quantum devices, validated via proof-of-concept on MNIST and CIFAR-10 image classification.
A slice-wise feature distillation framework for independent tensorization of neural network slices to achieve scalable compression with reduced fine-tuning costs.
Introduces two algorithms for efficient finite initialization of tensor network layers via iterative partial norm computations, applied to MPS/TT and MPO/TT-M layers with scaling analysis and public code.
A hybrid tensor network framework interpolates between classical and quantum models via controllable post-selection, with a trainable hyperparameter that complements bond dimension to enhance quantum machine learning.
ECG foundation models for signal interpretation and medical LLMs for reasoning can be integrated into agentic systems for real-time cardiovascular intelligence on edge devices.
Tensor networks developed for quantum states are reviewed as tools for machine learning models, with assessment of their potential computational, explanatory, and privacy advantages alongside remaining challenges.
citing papers explorer
-
Quantum-enhanced Large Language Models on Quantum Hardware via Cayley Unitary Adapters
Cayley unitary adapters executed on real quantum hardware improve LLM perplexity by 1.4% on Llama 3.1 8B with 6000 parameters and recover 83% of compression-induced degradation on SmolLM2.
-
Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification
A hybrid classical-quantum scheme compresses and disentangles bottleneck layers of pre-trained neural networks into MPO form for execution on quantum devices, validated via proof-of-concept on MNIST and CIFAR-10 image classification.
-
Fast Tensorization of Neural Networks via Slice-wise Feature Distillation
A slice-wise feature distillation framework for independent tensorization of neural network slices to achieve scalable compression with reduced fine-tuning costs.
-
Efficient Finite Initialization with Partial Norms for Tensorized Neural Networks and Tensor Networks Algorithms
Introduces two algorithms for efficient finite initialization of tensor network layers via iterative partial norm computations, applied to MPS/TT and MPO/TT-M layers with scaling analysis and public code.
-
Entanglement is Half the Story: Post-Selection vs. Partial Traces
A hybrid tensor network framework interpolates between classical and quantum models via controllable post-selection, with a trainable hyperparameter that complements bond dimension to enhance quantum machine learning.
-
ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook
ECG foundation models for signal interpretation and medical LLMs for reasoning can be integrated into agentic systems for real-time cardiovascular intelligence on edge devices.
-
Quantum-inspired tensor networks in machine learning models
Tensor networks developed for quantum states are reviewed as tools for machine learning models, with assessment of their potential computational, explanatory, and privacy advantages alongside remaining challenges.