English
Related papers

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

200 papers

This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT purports to generate an optimal trajectory, empirical evidence suggests it…

Machine Learning · Computer Science 2023-10-23 Yueh-Hua Wu , Xiaolong Wang , Masashi Hamaya

Shortcuts to adiabaticity~(STA) enables fast and robust coherent control of quantum system, which has been well placed in quantum technologies. In particular, inverse engineering STA provides much more freedom for the optimization of…

Quantum Physics · Physics 2024-12-17 Si-Qi Chen , He Lu

Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to convolutional UNets. However, the isotropic design of DiTs…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Quan Dao , Dimitris Metaxas

While self-attention has been instrumental in the success of Transformers, it can lead to over-concentration on a few tokens during training, resulting in suboptimal information flow. Enforcing doubly-stochastic constraints in attention…

Machine Learning · Computer Science 2025-07-15 Ashkan Shahbazi , Elaheh Akbari , Darian Salehi , Xinran Liu , Navid Naderializadeh , Soheil Kolouri

Tunneling field-effect transistors (TFETs) based on 2D materials are promising steep sub-threshold swing (SS) devices due to their tight gate control. There are two major methods to create the tunnel junction in these 2D TFETs: electrical…

Mesoscale and Nanoscale Physics · Physics 2016-08-30 Hesameddin Ilatikhameneh , Gerhard Klimeck , Joerg Appenzeller , Rajib Rahman

In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-efficient sequence modeling. However, existing Spiking Transformers still lack a…

Neural and Evolutionary Computing · Computer Science 2026-01-27 Sicheng Shen , Mingyang Lv , Bing Han , Dongcheng Zhao , Guobin Shen , Feifei Zhao , Yi Zeng

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available,…

Machine Learning · Computer Science 2023-03-21 Yongyi Su , Xun Xu , Tianrui Li , Kui Jia

We build a realistic Simultaneous Wireless Information and Power Transfer (SWIPT) prototype and experimentally analyse the harvested energy and throughput trade-off. Both time-switching and power splitting receiver architectures are…

Information Theory · Computer Science 2019-08-23 Junghoon Kim , Bruno Clerckx , Paul D. Mitcheson

The increasing computational demands of transformer models in time series classification necessitate effective optimization strategies for energy-efficient deployment. Our study presents a systematic investigation of optimization…

Machine Learning · Computer Science 2025-05-22 Arshia Kermani , Ehsan Zeraatkar , Habib Irani

The smart transformer (ST) implemented using power electronics converters, has the capability of independent voltage control and reactive power isolation between its primary and secondary terminals. This capability provides a flexibility in…

Systems and Control · Electrical Eng. & Systems 2019-11-18 Junru Chen , Ran Li , Alireza Soroudi , Andrew Keane , Damian Flynn , Terence ODonnell

The Advanced Superconducting Test Acccelerator (ASTA) is being constructed at Fermilab. The existing New Muon Lab (NML) building is being converted for this facility. The accelerator will consist of an electron gun, injector, beam…

The cornerstone of the Chinese experimental particle physics program consists of a series of experiments performed in the tau-charm energy region. China began building e+e- colliders at the Institute for High Energy Physics in Beijing more…

High Energy Physics - Experiment · Physics 2016-11-23 Roy A. Briere , Frederick A. Harris , Ryan E. Mitchell

In the last two and a half decades ion storage rings have proven to be powerful tools for precision experiments with unstable nuclides in realm of nuclear structure and astrophysics. There are presently three storage ring facilities in the…

Nuclear Experiment · Physics 2018-11-30 Y. H. Zhang , Yu. A. Litvinov , T. Uesaka , H. S. Xu

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…

Computation and Language · Computer Science 2026-05-20 Bowen Peng , Théo Gigant , Jeffrey Quesnelle

In this review, we give an overview of the proposed applications in the early-FTQC (EFTQC) era. Starting from the error correction architecture for EFTQC device, we first review the recently developed space-time efficient analogue rotation…

Quantum Physics · Physics 2024-09-13 Ming-Zhi Chung , Andreas Thomasen , Henry Liao , Ryosuke Imai

A set of nozzle equipment for proton therapy is now being developed at China Institute of Atomic Energy. To facilitate the off-line commissioning of the whole equipment, a set of ionization chamber signal generation system, the test…

Accelerator Physics · Physics 2025-10-22 Peng Huang , Zhiguo Yin , Tianjian Bian , Shigang Hou , Yang Wang , Tianjue Zhang , Luyu Ji , Lipeng Wen , Xueer Mu , Rui Xiong

Recent advancements in neutral atom platforms have enabled exploration of early fault-tolerant (FT) architectures for applications with quantum advantage, such as quantum dynamics simulations. An efficient fault-tolerant architecture has…

We present an on-chip trainable neuron circuit. Our proposed circuit suits bio-inspired spike-based time-dependent data computation for training spiking neural networks (SNN). The thresholds of neurons can be increased or decreased…

Neural and Evolutionary Computing · Computer Science 2024-03-07 Beyza Zeynep Ucpinar , Mustafa Altay Karamuftuoglu , Sasan Razmkhah , Massoud Pedram

Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of…

Machine Learning · Computer Science 2025-02-24 Velibor Bojković , Xiaofeng Wu , Bin Gu

Optimizing prices for energy demand response requires a flexible controller with ability to navigate complex environments. We propose a reinforcement learning controller with surprise minimizing modifications in its architecture. We suggest…

Machine Learning · Computer Science 2021-11-12 William Arnold , Tarang Srivastava , Lucas Spangher , Utkarsha Agwan , Costas Spanos
‹ Prev 1 4 5 6 7 8 10 Next ›