3 papers
cs.LG2026
LLM Compression by Block Removal with Constrained Binary Optimization
David Jansen, Roman Rausch, Ali Hashemi +2
In this paper, we formulate the compression of large language models (LLMs) by optimally deleting transformer blocks (``block removal'') as a constrained binary optimization (CBO)…
quant-ph2026
Pushing the Classical Frontier of 1D Fermi-Hubbard Quench Dynamics Beyond Current Quantum Simulations
Roman Rausch, Sukhbinder Singh, Saeed S. Jahromi +2
Establishing quantum advantage requires comparison against the best achievable classical simulation. The Q-CTRL team recently simulated quench dynamics of the one-dimensional Fermi…
cs.LG2025
Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing
Roman Rausch, David Jansen, Sukhbinder Singh +1
Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a…