MiniMax M2.5 Uses 10B Active Parameters per Token, Aiming for Cheaper Always-On Agents

MiniMax M2.5 hits about 80% on Sweetbench and runs near 100 tokens per second, helping teams deploy faster models on tighter budgets.
IEEE

Enhanced Sparse Bayesian Learning Methods with Application to Massive MIMO Channel Estimation

Abstract: We consider the problem of sparse channel estimation in massive multiple-input multiple-output systems. In this context, we propose an enhanced version of the sparse Bayesian learning (SBL) ...
IEEE

An Efficient Implementation of Small-Precision Floating-point Matrix Multiplication for AI-Based Image Processing Applications

Abstract: The Multiply and Accumulator (MAC) in Convolution Neural Network (CNN) for image applications demands an efficient matrix multiplier. This study presents an area- and power-efficient ...