Search papers, labs, and topics across Lattice.
Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
CMU Machine Learning3
0
4
A million p-bits in a single programmable architecture reveals a universal tradeoff between throughput and accuracy in distributed probabilistic computing.
Attention bottlenecks in long-context decoding? SANTA slashes memory bandwidth demands by stochastically sampling value vectors, achieving 1.5x speedups without sacrificing accuracy.
Variational learning can tame the inherent chaos of nanoscale devices, paving the way for practical, larger-scale probabilistic computers.
