3 papers
cs.LG2026
LegoLM: Structured Weight Sharing for Large Language Models
Joseph Bingham
We present \LegoLM{}, a structured weight-sharing compression framework for large language models grounded in a systematic study of why global weight sharing fails and how to fix i…
cs.AI2026
SOMtime the World Aint Fair: Violating Fairness Using Self-Organizing Maps
Joseph Bingham, Netanel Arussy, Dvir Aran
Unsupervised representations are widely assumed to be neutral with respect to sensitive attributes when those attributes are withheld from training. We show that this assumption is…
cs.LG2026
LegoNet: Memory Footprint Reduction Through Block Weight Clustering
Joseph Bingham, Noah Green, Saman Zonouz
As the need for neural network-based applications to become more accurate and powerful grows, so too does their size and memory footprint. With embedded devices, whose cache and RA…