Related papers: E2ATST: A Temporal-Spatial Optimized Energy-Effici…

In this paper, we take the advantage of previous pre-trained models (PTMs) and propose a novel Chinese Pre-trained Unbalanced Transformer (CPT). Different from previous Chinese PTMs, CPT is designed to utilize the shared knowledge between…

Reducing energy dissipation while increasing speed in computation and memory is a long-standing challenge for spintronics research. In the last 20 years, femtosecond lasers have emerged as a tool to control the magnetization in specific…

The electric control of quantum spin chains has been an outstanding goal for the few last years due to its potential use in technologies related to quantum information processing. In this work, we show the feasibility of the different steps…

As the role of artificial intelligence becomes increasingly pivotal in modern society, the efficient training and deployment of deep neural networks have emerged as critical areas of focus. Recent advancements in attention-based large…

Multi-energy systems can provide a constant level of service to end-use energy demands, while deriving delivered energy from a variety of primary/secondary energy sources. This fuel-switching capability can be used to reduce operating…

Transition-metal complexes (TMCs) are promising photosensitizers for Type~I photodynamic therapy (PDT), where electron-transfer processes can generate reactive oxygen species under hypoxic conditions. Yet identifying candidates with the…

Mitigating the climate crisis requires a rapid transition towards lower-carbon energy. Catalyst materials play a crucial role in the electrochemical reactions involved in numerous industrial processes key to this transition, such as…

Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the current mainstream of neuromorphic computing. By contrast, no…

The proliferation of IoT devices in smart cities challenges 6G networks with conflicting energy-latency requirements across heterogeneous slices. Existing approaches struggle with the energy-latency trade-off, particularly for massive scale…

Recent research has indicated that introducing impurities that increase the resistivity of Pt can enhance the efficiency of the spin Hall torque it generates. Here we directly demonstrate the usefulness of this strategy by fabricating…

The Five-hundred-meter Aperture Spherical radio Telescope(FAST) was launched on September 25,2016.From early 2017,we began to use the FAST wideband receiver,which was designed,constructed and installed on the FAST in Guizhou,China.The front…

In this work we propose a new supervised learning method for temporally-encoded multilayer spiking networks to perform classification. The method employs a reinforcement signal that mimics backpropagation but is far less computationally…

We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention. However, our model…

Electromagnetic transient (EMT) simulation is essential for analyzing sub-cycle switching phenomena in industrial power systems; however, commercial EMT platforms present significant cost barriers for smaller utilities, consultancies, and…

As we enter the exascale computing era, efficiently utilizing power and optimizing the performance of scientific applications under power and energy constraints has become critical and challenging. We propose a low-overhead autotuning…

Spiking Neural Networks (SNNs), with their brain-inspired spatiotemporal dynamics and spike-driven computation, have emerged as promising energy-efficient alternatives to Artificial Neural Networks (ANNs). However, existing SNNs typically…

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing…

Spiking Neural Networks (SNNs) offer energy efficient processing suitable for edge applications, but conventional sensor data must first be converted into spike trains for neuromorphic processing. Environmental sound, including urban…

Vision-language-action models have gained significant attention for their ability to model multimodal sequences in embodied instruction following tasks. However, most existing models rely on causal attention, which we find suboptimal for…

The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are…