# Tensorized Optical Multimodal Fusion Network

arXiv: https://arxiv.org/abs/2302.08744 · HTML: https://mlsanity.com/paper/2302.08744/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2023.

## Built on by (most cited first, 2 of 2)

- [Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization](https://mlsanity.com/paper/2501.06663/) (2025)
- [A Gradient-based Approach for Online Robust Deep Neural Network Training with Noisy Labels](https://mlsanity.com/paper/2306.05046/) (2023)

## Abstract (arXiv)

We propose the first tensorized optical multimodal fusion network architecture with a self-attention mechanism and low-rank tensor fusion. Simulation results show 51.3 × less hardware requirement and 3.7× 1013 MAC/J energy efficiency.