5 papers
CQ-CiM: Hardware-Aware Embedding Shaping for Robust CiM-Based Retrieval
Xinzhao Li, Alptekin Vardar, Franz Müller +6
Deploying Retrieval-Augmented Generation (RAG) on edge devices is in high demand, but is hindered by the latency of massive data movement and computation on traditional architectur…
Embedding-Enhanced Probabilistic Modeling of Ferroelectric Field Effect Transistors (FeFETs)
Tasnia Nobi Afee, Jack Hutchins, Md Mazharul Islam +2
FeFETs hold strong potential for advancing memory and logic technologies, but their inherent randomness arising from both operational cycling and fabrication variability poses sign…
Energy Efficient Dual Designs of FeFET-Based Analog In-Memory Computing with Inherent Shift-Add Capability
Zeyu Yang, Qingrong Huang, Yu Qian +3
In-memory computing (IMC) architecture emerges as a promising paradigm, improving the energy efficiency of multiply-and-accumulate (MAC) operations within DNNs by integrating the p…
FeBiM: Efficient and Compact Bayesian Inference Engine Empowered with Ferroelectric In-Memory Computing
Chao Li, Zhicheng Xu, Bo Wen +5
In scenarios with limited training data or where explainability is crucial, conventional neural network-based machine learning models often face challenges. In contrast, Bayesian i…
HyCiM: A Hybrid Computing-in-Memory QUBO Solver for General Combinatorial Optimization Problems with Inequality Constraints
Yu Qian, Zeyu Yang, Kai Ni +3
Computationally challenging combinatorial optimization problems (COPs) play a fundamental role in various applications. To tackle COPs, many Ising machines and Quadratic Unconstrai…