English
Related papers

Related papers: STEM: Scaling Transformers with Embedding Modules

200 papers

Spiking neural networks (SNNs) promise orders-of-magnitude efficiency gains by communicating with sparse, event-driven spikes rather than dense numerical activations. However, most training pipelines either rely on surrogate-gradient…

Neural and Evolutionary Computing · Computer Science 2025-12-17 Arman Ferdowsi , Atakan Aral

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

Machine Learning · Computer Science 2025-02-07 Zihao Huang , Qiyang Min , Hongzhi Huang , Defa Zhu , Yutao Zeng , Ran Guo , Xun Zhou

Semantic communication (SemCom) powered by generative artificial intelligence enables highly efficient and reliable information transmission. However, it still necessitates the transmission of substantial amounts of data when dealing with…

Information Theory · Computer Science 2025-06-17 Guojun Huang , Jiancheng An , Lu Gan , Dusit Niyato , Mérouane Debbah , Tie Jun Cui

Scanning transmission electron microscopy (STEM) is a powerful tool to reveal the morphologies and structures of materials, thereby attracting intensive interests from the scientific and industrial communities. The outstanding spatial…

Image and Video Processing · Electrical Eng. & Systems 2024-09-26 Hanlei Zhang , Jincheng Bai , Xiabo Chen , Can Li , Chuanjian Zhong , Jiye Fang , Guangwen Zhou

Transformers exhibit proficiency in capturing long-range dependencies, whereas State Space Models (SSMs) facilitate linear-time sequence modeling. Notwithstanding their synergistic potential, the integration of these architectures presents…

Computation and Language · Computer Science 2025-06-19 Bingheng Wu , Jingze Shi , Yifan Wu , Nan Tang , Yuyu Luo

Multivariate time series forecasting requires models to simultaneously capture variable-wise structural dependencies and generalize across diverse tasks. While structural encoders are effective in modeling feature interactions, they lack…

Computation and Language · Computer Science 2025-06-26 Fengze Li , Yue Wang , Yangle Liu , Ming Huang , Dou Hong , Jieming Ma

Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improvement--prioritizing data acquisition to close the largest performance gaps. We test whether an…

Computation and Language · Computer Science 2026-05-27 Pedro Memoli Buffa , Luciano Del Corro

Transformers have demonstrated exceptional performance across various domains due to their self-attention mechanism, which captures complex relationships in data. However, training on smaller datasets poses challenges, as standard attention…

Computation and Language · Computer Science 2024-12-10 Minhajur Rahman , Yasir Arafat

Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter…

Computation and Language · Computer Science 2026-01-30 Dabiao Ma , Ziming Dai , Zhimin Xin , Shu Wang , Jian Yang , Haojun Fei

Recommendation algorithms that incorporate techniques from deep learning are becoming increasingly popular. Due to the structure of the data coming from recommendation domains (i.e., one-hot-encoded vectors of item preferences), these…

Machine Learning · Computer Science 2017-06-14 Joan Serrà , Alexandros Karatzoglou

Structural Health Monitoring (SHM) is a critical task for ensuring the safety and reliability of civil infrastructures, typically realized on bridges and viaducts by means of vibration monitoring. In this paper, we propose for the first…

Can we use sparse tokens for dense prediction, e.g., segmentation? Although token sparsification has been applied to Vision Transformers (ViT) to accelerate classification, it is still unknown how to perform segmentation from sparse tokens.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Lei Zhou , Huidong Liu , Joseph Bae , Junjun He , Dimitris Samaras , Prateek Prasanna

Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders to refine low-quality queries. We present HELP…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Yangchen Zeng , Zhenyu Yu , Dongming Jiang , Wenbo Zhang , Yifan Hong , Zhanhua Hu , Jiao Luo , Kangning Cui

Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing. However, deploying NNs in resource-constrained safety-critical systems has challenges due to uncertainty in the…

Machine Learning · Computer Science 2024-01-17 Soyed Tuhin Ahmed

To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly…

Machine Learning · Computer Science 2023-06-05 Yu Yang , Hao Kang , Baharan Mirzasoleiman

As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer(ST)-based models…

Machine Learning · Computer Science 2026-01-06 Hongze Sun , Wuque Cai , Duo Chen , Quan Tang , Shifeng Mao , Jiayi He , Zhenxing Wang , Yan Cui , Dezhong Yao , Daqing Guo

Spiking neural networks (SNNs) have shown a potential for having low energy with unsupervised learning capabilities due to their biologically-inspired computation. However, they may suffer from accuracy degradation if their processing is…

Hardware Architecture · Computer Science 2023-03-06 Rachmad Vidya Wicaksana Putra , Muhammad Abdullah Hanif , Muhammad Shafique

Four-dimensional scanning transmission electron microscopy (4D-STEM) enables mapping of diffraction information with nanometer-scale spatial resolution, offering detailed insight into local structure, orientation, and strain. However, as…

Compressed file formats are the corner stone of efficient data storage and transmission, yet their potential for representation learning remains largely underexplored. We introduce TEMPEST (TransformErs froM comPressed rEpreSenTations), a…

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the…

Computation and Language · Computer Science 2024-12-17 Zekai Li , Jintu Zheng , Ji Liu , Han Liu , Haowei Zhu , Zeping Li , Fuwei Yang , Haiduo Huang , Jinzhang Peng , Dong Li , Lu Tian , Emad Barsoum