2 papers
cs.LG2026
The Effect of Quantization on Clinical Benchmarks: Accuracy and Safety Across Model Families
Leonard Twagirayezu, Prasenjit Mitra
Quantization enables deployment of large language models on resource-constrained clinical edge devices, but its effect on clinical accuracy and safety remains understudied. We eval…
cs.AI2026
Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for Energy-Efficient LLM Deployment
Leonard Twagirayezu, Prasenjit Mitra
Large Reasoning Models (LRMs) impose substantial energy costs during deployment, yet current compression methods apply uniform quantization across all components, risking damage to…