English
Related papers

Related papers: Revisiting Transformer Layer Parameterization Thro…

200 papers

The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mechanism for Explanations), a method for generating explanation…

Computer Vision and Pattern Recognition · Computer Science 2025-01-30 Mariano Ntrougkas , Nikolaos Gkalelis , Vasileios Mezaris

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Zizheng Pan , Bohan Zhuang , Haoyu He , Jing Liu , Jianfei Cai

Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Pooyan Rahmanzadehgervi , Hung Huy Nguyen , Rosanne Liu , Long Mai , Anh Totti Nguyen

The Transformer architecture has become prominent in developing large causal language models. However, mechanisms to explain its capabilities are not well understood. Focused on the training process, here we establish a meta-learning view…

Machine Learning · Computer Science 2024-03-26 Xinbo Wu , Lav R. Varshney

The multi-head self-attention of popular transformer models is widely used within Natural Language Processing (NLP), including for the task of extractive summarization. With the goal of analyzing and pruning the parameter-heavy…

Computation and Language · Computer Science 2020-12-04 Wen Xiao , Patrick Huber , Giuseppe Carenini

The Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model. Additionally, recent works have demonstrated that…

Computation and Language · Computer Science 2022-10-25 Javier Ferrando , Gerard I. Gállego , Marta R. Costa-jussà

Cooperative energy recycling (CER) offers a new way to boost energy utilization in wireless-powered multi-access edge computing (MEC) networks, yet its integration with computation-communication co-design remains underexplored. This paper…

Information Theory · Computer Science 2025-11-05 Haohao Qin , Bowen Gu , Xianhua Yu , Hao Xie , Yongjun Xu , Qihao Li , Liejun Wang

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

Machine learning (ML) algorithms, particularly attention-based transformer models, have become indispensable for analyzing the vast data generated by particle physics experiments like ATLAS and CMS at the CERN LHC. Particle Transformer…

High Energy Physics - Phenomenology · Physics 2024-12-10 Aaron Wang , Abhijith Gandrakota , Jennifer Ngadiuba , Vivekanand Sahu , Priyansh Bhatnagar , Elham E Khoda , Javier Duarte

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this…

Machine Learning · Computer Science 2024-06-04 Romain Ilbert , Ambroise Odonnat , Vasilii Feofanov , Aladin Virmaux , Giuseppe Paolo , Themis Palpanas , Ievgen Redko

The evolution of large language models (LLMs) towards applications with ultra-long contexts faces challenges posed by the high computational and memory costs of the Transformer architecture. While existing sparse and linear attention…

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

Transformer-based models achieve favorable performance in artistic style transfer recently thanks to its global receptive field and powerful multi-head/layer attention operations. Nevertheless, the over-paramerized multi-layer structure…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Hao Tang , Songhua Liu , Tianwei Lin , Shaoli Huang , Fu Li , Dongliang He , Xinchao Wang

Transformer is a transformative framework that models sequential data and has achieved remarkable performance on a wide range of tasks, but with high computational and energy cost. To improve its efficiency, a popular choice is to compress…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Jing Liu , Zizheng Pan , Haoyu He , Jianfei Cai , Bohan Zhuang

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Machine Learning · Computer Science 2025-07-15 Sai Surya Duvvuri , Inderjit S. Dhillon

Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer…

Computation and Language · Computer Science 2024-12-17 Neha Verma , Maha Elbayad

The stacked intelligent metasurface (SIM), comprising multiple layers of reconfigurable transmissive metasurfaces, is becoming an increasingly viable solution for future wireless communication systems. In this paper, we explore the…

Information Theory · Computer Science 2025-04-23 Enyu Shi , Jiayi Zhang , Jiancheng An , Marco Di Renzo , Bo Ai , Chau Yuen

Recent research has established that the impact of context in a vanilla transformer can be represented implicitly by forming a token-dependent, rank-1 patch to its MLP weights. This work extends that foundational theory to the diverse…

Machine Learning · Computer Science 2025-12-24 Adrian Goldwaser , Michael Munn , Javier Gonzalvo , Benoit Dherin

Self-attention is usually described as a flexible, content-adaptive way to mix a token with information from its past. We reinterpret causal self-attention transformers, the backbone of modern foundation models, within a probabilistic…

Machine Learning · Computer Science 2026-03-24 Deepak Agarwal , Dhyey Dharmendrakumar Mavani , Suyash Gupta , Karthik Sethuraman , Tejas Dharamsi

The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies. However, as the demand for understanding complex relationships grows,…

Computation and Language · Computer Science 2024-06-18 Qian Chen , Wen Wang , Qinglin Zhang , Siqi Zheng , Shiliang Zhang , Chong Deng , Hai Yu , Jiaqing Liu , Yukun Ma , Chong Zhang