Related papers: A Low-Dissipation and Scalable GEMM Accelerator wi…
Microcombs have sparked a surge of applications over the last decade, ranging from optical communications to metrology. Despite their diverse deployment, most microcomb-based systems rely on a tremendous amount of bulk equipment to fulfill…
Silicon-organic hybrid (SOH) platforms exhibit exceptional electro-optic (EO) properties, including high-speed operation, low energy consumption, and compact footprints. However, the absence of a scalable poling method for EO polymers,…
The recent progress of artificial intelligence (AI) has boosted the computational possibilities in fields where standard computers are not able to perform. The AI paradigm is to emulate human intelligence and therefore breaks the familiar…
Deep learning-driven superresolution (SR) outperforms traditional techniques but also faces the challenge of high complexity and memory bandwidth. This challenge leads many accelerators to opt for simpler and shallow models like FSRCNN,…
Convolutional neural network (CNN) inference on mobile devices demands efficient hardware acceleration of low-precision (INT8) general matrix multiplication (GEMM). Exploiting data sparsity is a common approach to further accelerate GEMM…
We present the first algorithm that implements an abstract MAC (absMAC) layer in the Signal-to-Interference-plus-Noise-Ratio (SINR) wireless network model. We first prove that efficient SINR implementations are not possible for the standard…
Sparse deep learning has reduced computation significantly, but its irregular non-zero data distribution complicates the data flow and hinders data reuse, increasing on-chip SRAM access and thus power consumption of the chip. This paper…
Aluminum nitride (AlN) is an emerging material for integrated quantum photonics due to its large $\chi^{(2)}$ nonlinearity. Here we demonstrate the hybrid integration of AlN on silicon nitride (SiN) photonic chips. Composite microrings are…
The Silicon Photomultiplier (SiPM) is a mature photodetector concept that is applied in a variety of applications ranging from medical imaging to automotive LiDAR systems. Over the last few years, improvements of the sensor performance are…
The evolution of quantization and mixed-precision techniques has unlocked new possibilities for enhancing the speed and energy efficiency of NNs. Several recent studies indicate that adapting precision levels across different parameters can…
Synthetic aperture radar (SAR) tomography (TomoSAR) enables the reconstruction and three-dimensional (3D) localization of targets based on multiple two-dimensional (2D) observations of the same scene. The resolving along the elevation…
We analyze the steady-state transmission of high-momentum (high-$k$) electromagnetic waves through metal-semiconductor multilayer systems with loss and gain in the near-infrared (NIR). Using a semi-classical optical gain model in…
High stress stoichiometric silicon nitride resonators, whose quality factors exceed one million, have shown promise for applications in sensing and signal processing. Yet, electrical integration of the insulating silicon nitride resonators…
Photonic computing is a compelling avenue for performing highly efficient matrix multiplication, a crucial operation in Deep Neural Networks (DNNs). While this method has shown great success in DNN inference, meeting the high precision…
Accurately predicting adsorption properties in nanoporous materials using Deep Learning models remains a challenging task. This challenge becomes even more pronounced when attempting to generalize to structures that were not part of the…
Matrix-multiplication units (MXUs) are now prevalent in every computing platform. The key attribute that makes MXUs so successful is the semiring structure, which allows tiling for both parallelism and data reuse. Nonetheless,…
In the early stages of semiconductor equipment development, obtaining large quantities of raw optical images poses a significant challenge. This data scarcity hinder the advancement of AI-powered solutions in semiconductor manufacturing. To…
The rapid advancement of Large Language Models (LLMs) has revolutionized various aspects of human life, yet their immense computational and energy demands pose significant challenges for efficient inference. The memory wall, the growing…
The unprecedented advancement of artificial intelligence has placed immense demands on computing hardware, but traditional silicon-based semiconductor technologies are approaching their physical and economic limit, prompting the exploration…
With the increasing need for large volumes of data processing, transport, and storage, optimizing the trade-off between high-speed and energy consumption in today's optoelectronic devices is getting increasingly difficult. Heterogeneous…