English
Related papers

Related papers: Learning to Skip the Middle Layers of Transformers

200 papers

Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Davide Abati , Jakub Tomczak , Tijmen Blankevoort , Simone Calderara , Rita Cucchiara , Babak Ehteshami Bejnordi

The attention mechanism is the primary component of the transformer architecture; it has led to significant advancements in deep learning spanning many domains and covering multiple tasks. In computer vision, the attention mechanism was…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Abdullah Nazhat Abdullah , Tarkan Aydin

Transformer-based language models create hidden representations of their inputs at every layer, but only use final-layer representations for prediction. This obscures the internal decision-making process of the model and the utility of its…

Computation and Language · Computer Science 2024-06-21 Alexander Yom Din , Taelin Karidi , Leshem Choshen , Mor Geva

In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…

Machine Learning · Computer Science 2025-05-29 Gleb Gerasimov , Yaroslav Aksenov , Nikita Balagansky , Viacheslav Sinii , Daniil Gavrilov

Data Prefetching is a technique that can hide memory latency by fetching data before it is needed by a program. Prefetching relies on accurate memory access prediction, to which task machine learning based methods are increasingly applied.…

Hardware Architecture · Computer Science 2022-05-31 Pengmiao Zhang , Ajitesh Srivastava , Anant V. Nori , Rajgopal Kannan , Viktor K. Prasanna

Topology optimization enables the design of highly efficient and complex structures, but conventional iterative methods, such as SIMP-based approaches, often suffer from high computational costs and sensitivity to initial conditions.…

Computational Engineering, Finance, and Science · Computer Science 2025-09-18 Aaron Lutheran , Srijan Das , Alireza Tabarraei

Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to…

Machine Learning · Computer Science 2023-10-04 Zihan Pengmei , Zimu Li , Chih-chan Tien , Risi Kondor , Aaron R. Dinner

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and…

Machine Learning · Computer Science 2021-06-03 Hanxiao Liu , Zihang Dai , David R. So , Quoc V. Le

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low-level features can become harder to recover as the residual stream is repeatedly…

Machine Learning · Computer Science 2026-05-07 Skye Gunasekaran , Téa Wright , Rui-Jie Zhu , Jason Eshraghian

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks. Multi-token prediction (MTP) has recently emerged as a promising alternative,…

Machine Learning · Computer Science 2026-04-15 Jianhao Huang , Zhanpeng Zhou , Renqiu Xia , Baharan Mirzasoleiman , Weijie Su , Wei Huang

We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing…

Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This bias is closely connected to the Lost-in-the-Middle phenomenon, where models underutilize…

Machine Learning · Computer Science 2026-05-28 Hanna Herasimchyk , Robin Labryga , Tomislav Prusina , Sören Laue

Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, there is limited theoretical analysis on why these models…

Machine Learning · Statistics 2026-03-19 Nil Ayday , Lingchu Yang , Debarghya Ghoshdastidar

Transformers perform inference by iteratively transforming token representations across layers. This layerwise computation has been studied empirically, and recent mean-field theories of Transformer dynamics explain how attention can drive…

Machine Learning · Computer Science 2026-05-11 Noboru Isobe , Daisuke Inoue , Masaaki Imaizumi

Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are beneficial to graph transformers, and find that current…

Machine Learning · Computer Science 2023-03-02 Haiteng Zhao , Shuming Ma , Dongdong Zhang , Zhi-Hong Deng , Furu Wei

A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in…

Machine Learning · Statistics 2016-08-15 Trang Pham , Truyen Tran , Dinh Phung , Svetha Venkatesh

We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features at different input…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Barry Shichen Hu , Siyun Liang , Johannes Paetzold , Huy H. Nguyen , Isao Echizen , Jiapeng Tang

Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new…

Machine Learning · Computer Science 2025-08-27 Dylan Cutler , Arun Kandoor , Nishanth Dikkala , Nikunj Saunshi , Xin Wang , Rina Panigrahy