相关论文: Computational Associative Memory with Amorphous In…

The use of 1-bit analog-to-digital converters (ADCs) is seen as a promising approach to significantly reduce the power consumption and hardware cost of multiple-input multiple-output (MIMO) receivers. However, the nonlinear distortion due…

Thin-film transistors based on amorphous oxide semiconductors (AOS) are promising candidates for enabling further DRAM scaling and 3D integration, which are critical for advanced computing. Despite extensive research, the charge transport…

Scalability and performance of current flash memories can be improved substantially by replacing the floating poly-Si gate by a layer of Si dots. This multi-dot layer can be fabricated CMOS-compatibly in very thin gate oxide by ion beam…

This work demonstrates a large area process for atomically thin 2D semiconductors to unlock the technological upscale required for their commercial uptake. The new atomic layer deposition (ALD) and conversion technique yields large area…

Dynamic 3D Gaussian splatting (3DGS) extends static 3DGS to render dynamic scenes, enabling AR/VR applications with moving objects. However, implementing dynamic 3DGS on edge devices faces challenges: (1) Loading all Gaussian parameters…

Scalable, high-speed, small-footprint photonic switching platforms are essential for advancing optical communication. An effective optical switch must operate at high duty cycles with fast recovery times, while maintaining substantial…

Aside from recent advances in artificial intelligence (AI) models, specialized AI hardware is crucial to address large volumes of unstructured and dynamic data. Hardware-based AI, built on conventional complementary metal-oxidesemiconductor…

The Quantum Diamond Microscope (QDM) is an emerging magnetic imaging tool enabling noninvasive characterization of electronic circuits through spatially mapping current densities. In this work, we demonstrate wafer-level current sensing of…

Scaling transistors' dimensions has been the thrust for the semiconductor industry in the last 4 decades. However, scaling channel lengths beyond 10 nm has become exceptionally challenging due to the direct tunneling between source and…

While memory-augmented neural networks (MANNs) offer an effective solution for few-shot learning (FSL) by integrating deep neural networks with external memory, the capacity requirements and energy overhead of data movement become enormous…

We have modified a commercial NOR flash memory array to enable high-precision tuning of individual floating-gate cells for analog computing applications. The modified array area per cell in a 180 nm process is about 1.5 um^2. While this…

For the past four decades, cost and features have driven CMOS scaling. Severe lithography and material limitations seen below the 20 nm node, however, are challenging the fundamental premise of affordable CMOS scaling. Just continuing to…

Content Addressable Memories (CAMs) are considered a key-enabler for in-memory computing (IMC). IMC shows order of magnitude improvement in energy efficiency and throughput compared to traditional computing techniques. Recently, analog CAMs…

Orthogonal time frequency space (OTFS) modulation offers superior robustness to high-mobility channels compared to conventional orthogonal frequency-division multiplexing (OFDM) waveforms. However, its explicit delay-Doppler (DD) domain…

Analog Content Addressable Memories (aCAMs) have proven useful for associative in-memory computing applications like Decision Trees, Finite State Machines, and Hyper-dimensional Computing. While non-volatile implementations using FeFETs and…

High performance InGaAs gate-all-around (GAA) nanowire MOSFETs with channel length (Lch) down to 20nm have been fabricated by integrating a higher-k LaAlO3-based gate stack with an equivalent oxide thickness of 1.2nm. It is found that…

Two-dimensional (2D) semiconductors have been suggested both for ultimately-scaled field-effect transistors (FETs) and More-than-Moore nanoelectronics. However, these targets can not be reached without accompanying gate insulators which are…

Charge-trap memory with high-\k dielectric materials is considered to be a promising candidate for next-generation memory devices. Ultrathin layered two-dimensional (2D) materials like graphene and MoS2 have been receiving much attention…

In contemporary general-purpose graphics processing units (GPGPUs), the continued increase in raw arithmetic throughput is constrained by the capabilities of the register file (single-cycle) and last-level cache (high bandwidth), which…

Synaptic devices with linear high-speed switching can accelerate learning in artificial neural networks (ANNs) embodied in hardware. Conventional resistive memories however suffer from high write noise and asymmetric conductance tuning,…