Lucius Vo · Library

Publications

An archive of papers, preprints, and book chapters — the questions I've been chasing on the page.

2026 SIAM Conference on Parallel Processing for Scientific Computing (PP26)

From GPUs to RRAMs: Distributed In-Memory Primal-Dual Hybrid Gradient Method for Solving Large-Scale Linear Optimization Problems

Huynh Q. N. Vo, Md Tawsif Rahman Chowdhury, Paritosh Ramanan, Gozde Tutuncuoglu, Junchi Yang, Feng Qiu, and Murat Yildirim. (2026). From GPUs to RRAMs: Distributed In-Memory Primal-Dual Hybrid Gradient Method for Solving Large-Scale Linear Optimization Problems. In: Proceedings of the 2026 SIAM Conference on Parallel Processing for Scientific Computing (PP26).

We present a distributed primal-dual hybrid gradient (PDHG) method co-designed for resistive random-access memory (RRAM) in-memory computing, enabling large-scale linear optimization with dramatically reduced energy and latency compared to GPU baselines.

Read details →

arXiv preprint

Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction

Huynh Q. N. Vo, Md Tawsif Rahman Chowdhury, Paritosh Ramanan, Murat Yildirim, and Gozde Tutuncuoglu. (2025). Harnessing the Full Potential of RRAMs through Scalable and Distributed In-Memory Computing with Integrated Error Correction. arXiv preprint arXiv:2508.13298.

We introduce MELISO+: a distributed, full-stack RRAM in-memory computing framework with integrated two-tier error correction for scalable, high-dimensional matrix computations.

Read details →

2024 IEEE International Conference on Big Data (BigData)

SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems

H. M. M. Islam, H. Q. N. Vo and P. Ramanan, "SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems", in 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA, 2024, pp. 938-948.

We present SplitVAE, a decentralized scenario generation framework that leverages variational autoencoders to generate high-quality scenarios without moving stakeholder data.

Read details →

2024 International Conference on Neuromorphic Systems (ICONS'24)

The Lynchpin of In-Memory Computing: A Benchmarking Framework for Vector-Matrix Multiplication in RRAMs

M. T. Rahman Chowdhury, H. Q. Nguyen Vo, P. Ramanan, M. Yildirim and G. Tutuncuoglu, "The Lynchpin of In-Memory Computing: A Benchmarking Framework for Vector-Matrix Multiplication in RRAMs," 2024 International Conference on Neuromorphic Systems (ICONS), Arlington, VA, USA, 2024, pp. 336-342.

We introduce MELISO (In-Memory Linear Solver), a comprehensive end-to-end VMM benchmarking framework tailored for RRAM-based systems. MELISO evaluates the error propagation in VMM operations, analyzing the impact of RRAM device metrics on error magnitude and distribution.

Read details →

Optical Review

Measurement setup for differential spectral responsivity of solar cells

Kärhä, P., Baumgartner, H., Askola, J. et al. Measurement setup for differential spectral responsivity of solar cells. Opt Rev 27, 195–204 (2020).

We present a setup for measuring differential spectral responsivities of unifacial and bifacial solar cells under bias light conditions.

Read details →