Matthew Brand — accepted AI-conference papers

2026

LatentLLM: Activation-Aware Transform to Multi-Head Latent Attention

Toshiaki Koike-Akino, Xiangyu Chen, Jing Liu, Ye Wang, Pu (Perry) Wang, Matthew Brand

AAAI 2026technical

Modern foundation models such as large language models (LLMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs into a reduced-dimension latent structure. Our method extends a local activation-aware tensor decomposition to a global attent

Cited by 0 Source ↗PDF ↗Scholar ↗

2017

Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks

Ziming Zhang, Matthew Brand

NeurIPS 2017poster

By lifting the ReLU function into a higher dimensional space, we develop a smooth multi-convex formulation for training feed-forward deep neural networks (DNNs). This allows us to develop a block coordinate descent (BCD) training algorithm consisting of a sequence of numerically well-behaved convex…

Cited by 96 Source ↗PDF ↗Scholar ↗