English
Related papers

Related papers: HybridNorm: Towards Stable and Efficient Transform…

200 papers

Quantum convolutional neural networks (QCNNs) offer a promising architecture for near-term quantum machine learning by combining hierarchical feature extraction with modest parameter growth. However, any QCNN operating on classical data…

Quantum Physics · Physics 2025-12-16 Xingyun Feng

Decoder-only transformer networks have become incredibly popular for language modeling tasks. State-of-the-art models can have over a hundred transformer blocks, containing billions of trainable parameters, and are trained on trillions of…

Computation and Language · Computer Science 2025-05-13 Isaac Gerber

In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the Hessian matrix, and the maximum tolerable learning rate. We…

Machine Learning · Computer Science 2026-02-03 Marco Chen , Xianbiao Qi , Yelin He , Jiaquan Ye , Rong Xiao

Transformer with self-attention has achieved great success in the area of nature language processing. Recently, there have been a few studies on transformer for end-to-end speech recognition, while its application for hybrid acoustic model…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-24 Liang Lu

Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords as basic units in developing such systems. However, the…

Computation and Language · Computer Science 2023-05-29 Bei Li , Yi Jing , Xu Tan , Zhen Xing , Tong Xiao , Jingbo Zhu

This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence…

Computation and Language · Computer Science 2024-02-06 Vukasin Bozic , Danilo Dordevic , Daniele Coppola , Joseph Thommes , Sidak Pal Singh

Deep learning has recently garnered significant interest in wireless communications due to its superior performance compared to traditional model-based algorithms. Deep convolutional neural networks (CNNs) have demonstrated notable…

Signal Processing · Electrical Eng. & Systems 2025-09-22 SaiKrishna Saketh Yellapragada , Esa Ollila , Mario Costa

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Thomas De Min , Massimiliano Mancini , Karteek Alahari , Xavier Alameda-Pineda , Elisa Ricci

Quantum machine learning has emerged as a potential practical application of near-term quantum devices. In this work, we study a two-layer hybrid classical-quantum classifier in which a first layer of quantum stochastic neurons implementing…

Quantum Physics · Physics 2022-05-11 Ivana Nikoloska , Osvaldo Simeone

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing computational overhead. Self-attention integrates learnable query and key matrices to…

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Computation and Language · Computer Science 2026-04-16 Jusen Du , Jiaxi Hu , Tao Zhang , Weigao Sun , Yu Cheng

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Zihang Dai , Hanxiao Liu , Quoc V. Le , Mingxing Tan

Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise…

Machine Learning · Computer Science 2015-06-09 Zhiyuan Tang , Dong Wang , Yiqiao Pan , Zhiyong Zhang

Hybrid systems are prevalent in robotics. However, ensuring the stability of hybrid systems is challenging due to sophisticated continuous and discrete dynamics. A system with all its system modes stable can still be unstable. Hence special…

Robotics · Computer Science 2023-03-21 Yue Meng , Chuchu Fan

This paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The…

Multi-task learning (MTL) is a novel framework to learn several tasks simultaneously with a single shared network where each task has its distinct personalized header network for fine-tuning. MTL can be implemented in federated learning…

Machine Learning · Computer Science 2022-03-28 Matin Mortaheb , Cemil Vahapoglu , Sennur Ulukus

The design choices in Transformer feed-forward neural networks have resulted in significant computational and parameter overhead. In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often…

Computation and Language · Computer Science 2024-06-06 Tong Zheng , Bei Li , Huiwen Bao , Jiale Wang , Weiqiao Shan , Tong Xiao , Jingbo Zhu

In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet. The first branch receives supervision signal and…

Machine Learning · Computer Science 2018-07-31 Thomas Robert , Nicolas Thome , Matthieu Cord

The rapid evolution of Large Language Models (LLMs), epitomized by architectures like GPT-4, has reshaped the landscape of natural language processing. This paper introduces a pioneering approach to address the efficiency concerns…

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…

Machine Learning · Computer Science 2026-02-02 Shyam Venkatasubramanian , Sean Moushegian , Michael Lin , Mir Park , Ankit Singhal , Connor Lee