Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding
Ziteng Sun, Adrian Benton, Samuel Kushnir +4
Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization leve…
cs.LG2024
On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study
Tomoyoshi Kimura, Jinyang Li, Tianshi Wang +9
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a cla…