Brian Coyle
@brianc2095.bsky.social
Staff Scientist at QCWare //
Quantum machine learning //
Quantum computing
Quantum machine learning //
Quantum computing
Very happy with how this work conceived and led by @snehalraj.bsky.social turned out! The first of many from his joint PhD with QCWare and @sorbonne-universite.fr.
An excellent example of how ideas inspired from quantum computing can be used in foundational ML models *right now*.
An excellent example of how ideas inspired from quantum computing can be used in foundational ML models *right now*.
Our work, "Hyper Compressed Fine-Tuning of Large Foundation Models with Quantum Inspired Adapters" is now on arXiv! scirate.com/arxiv/2502.0... Our methods can compress large models by up to 44x with minimal performance loss.
Hyper Compressed Fine-Tuning of Large Foundation Models with Quantum Inspired Adapters
Fine-tuning pre-trained large foundation models for specific tasks has become increasingly challenging due to the computational and storage demands associated with full parameter updates. Parameter-Ef...
scirate.com
February 12, 2025 at 3:23 PM
Very happy with how this work conceived and led by @snehalraj.bsky.social turned out! The first of many from his joint PhD with QCWare and @sorbonne-universite.fr.
An excellent example of how ideas inspired from quantum computing can be used in foundational ML models *right now*.
An excellent example of how ideas inspired from quantum computing can be used in foundational ML models *right now*.