Related papers: Large-Scale Integrated Vector-Matrix Multiplicatio…
Machine learning and data analytics applications increasingly suffer from the high latency and energy consumption of conventional von Neumann architectures. Recently, several in-memory and near-memory systems have been proposed to remove…
Convolutional Neural Networks (CNNs) are rapidly gaining popularity in varied fields. Due to their increasingly deep and computationally heavy structures, it is difficult to deploy them on energy constrained mobile applications. Hardware…
Latency and energy consumption are key metrics in the performance of deep neural network (DNN) accelerators. A significant factor contributing to latency and energy is data transfers. One method to reduce transfers or data is reusing data…
Vertical integration of two-dimensional (2D) van der Waals (vdW) materials with different quantum ground states is predicted to lead to novel electronic properties that are not found in the constituent layers. Here, we present the direct…
In view of their immensely intriguing properties, two dimensional materials are being intensely researched in search of novel phenomena and diverse application interests, however, studies on the realization of nanocomposites in the…
As large language models (LLMs) continue to scale up, mixture-of-experts (MoE) has become a common technology in SOTA models. MoE models rely on expert parallelism (EP) to alleviate memory bottleneck, which introduces all-to-all…
Co-exploration of neural architectures and hardware design is promising to simultaneously optimize network accuracy and hardware efficiency. However, state-of-the-art neural architecture search algorithms for the co-exploration are…
Silicon-based dielectric nanoantennas provide an effective platform for engineering light-matter interactions in van der Waals semiconductors. Here, we demonstrate near-field coupling between monolayer MoS2 and silicon nanoantennas arranged…
Heterostructures play significant roles in modern semiconductor devices and micro/nanosystems in a plethora of applications in electronics, optoelectronics, and transducers. While state-of-the-art heterostructures often involve stacks of…
Moir\'e materials provide an ideal platform for exploring quantum phases of matter. However, solving the many-electron problem in moir\'e systems is challenging due to strong correlation effects. We introduce a powerful variational…
We present a graphene-based memory platform built on dual-gated field-effect transistors (GFETs). By integrating a lithographically defined metal patch directly atop the hexagonal boron nitride (hBN)-graphene channel, the device functions…
Due to its high carrier mobility, broadband absorption, and fast response time, graphene is attractive for optoelectronics and photodetection applications. However, the extraction of photoelectrons in conventional metal-graphene junction…
Deep neural networks are an extremely successful and widely used technique for various pattern recognition and machine learning tasks. Due to power and resource constraints, these computationally intensive networks are difficult to…
Van der Waals integration enables the creation of electronic and optoelectronic devices with unprecedented performance and novel functionalities beyond the existing material limitations. However, it is typically realized using a physical…
Transformer-based large language models are a memory-bound model whose operation is based on a large amount of data that are marginally reused. Thus, the data movement between a host and accelerator likely dictates the total wall-clock…
In recent years fused-multiply-add (FMA) units with lower-precision multiplications and higher-precision accumulation have proven useful in machine learning/artificial intelligence applications, most notably in training deep neural networks…
Very large-scale integration of devices in a circular pattern has several advantages over the commonly used rectangular grid layout. For the development of such integrated circuits on a 2D semiconductor platform, spontaneous growth of the…
Vertically stacked van der Waals heterostructures are a lucrative platform for exploring the rich electronic and optoelectronic phenomena in two-dimensional materials. Their performance will be strongly affected by impurities and defects at…
The advent of microcomputers in the 1970s has dramatically changed our society. Since then, microprocessors have been made almost exclusively from silicon, but the ever-increasing demand for higher integration density and speed, lower power…
Two-dimensional (2D) materials have attracted a great deal of interest in recent years. This family of materials allows for the realization of versatile electronic devices and holds promise for next-generation (opto)electronics. Their…