English
Related papers

Related papers: Understanding and Improving Transformer From a Mul…

200 papers

Transformer architectures are typically described in algorithmic and statistical terms, leaving their internal mechanics without a familiar structural language for researchers trained in physical theories. To bridge this gap, we develop a…

Disordered Systems and Neural Networks · Physics 2026-03-18 Po-Hao Chang

Algorithmic reasoning requires capabilities which are most naturally understood through recurrent models of computation, like the Turing machine. However, Transformer models, while lacking recurrence, are able to perform such reasoning…

Machine Learning · Computer Science 2023-05-03 Bingbin Liu , Jordan T. Ash , Surbhi Goel , Akshay Krishnamurthy , Cyril Zhang

This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network…

Computation and Language · Computer Science 2025-11-03 Shang Wang , Huanrong Tang , Jianquan Ouyang

Orthogonal frequency division multiplexing (OFDM) has been recently recognized as inadequate to meet the increased requirements of the next generation of communication systems. A number of alternative modulation solutions, based on the use…

Information Theory · Computer Science 2016-07-14 Konstantinos Maliatsos , Eleftherios Kofidis , Athanasios Kanatas

In the article, we discuss the architecture of the polynomial neural network that corresponds to the matrix representation of Lie transform. The matrix form of Lie transform is an approximation of the general solution of the nonlinear…

Neural and Evolutionary Computing · Computer Science 2019-08-19 Andrei Ivanov , Alena Sholokhova , Sergei Andrianov , Roman Konoplev-Esgenburg

This paper proposes a Transformer-based model to generate equations for math word problems. It achieves much better results than RNN models when copy and align mechanisms are not used, and can outperform complex copy and align RNN models.…

Machine Learning · Computer Science 2019-08-30 Yuanliang Meng , Anna Rumshisky

Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed…

Artificial Intelligence · Computer Science 2026-02-10 Ziyang Zheng , Jiaying Zhu , Jingyi Zhou , Qiang Xu

Attention-based Encoder-Decoder has the effective architecture for neural machine translation (NMT), which typically relies on recurrent neural networks (RNN) to build the blocks that will be lately called by attentive reader during the…

Computation and Language · Computer Science 2017-12-07 Hao Xiong , Zhongjun He , Xiaoguang Hu , Hua Wu

Developing neural architectures that are capable of logical reasoning has become increasingly important for a wide range of applications (e.g., natural language processing). Towards this grand objective, we propose a symbolic reasoning…

Computation and Language · Computer Science 2022-10-25 Jianyi Zhang , Yiran Chen , Jianshu Chen

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Computation and Language · Computer Science 2021-02-17 Mikhail S. Burtsev , Yuri Kuratov , Anton Peganov , Grigory V. Sapunov

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…

Computation and Language · Computer Science 2020-07-09 Prajjwal Bhargava

In modern machine (ML) learning systems, Transformer-based architectures have achieved milestone success across a broad spectrum of tasks, yet understanding their operational mechanisms remains an open problem. To improve the transparency…

Machine Learning · Computer Science 2024-06-11 Yihao Zhang , Zeming Wei , Meng Sun

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

Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of Transformer networks…

Computation and Language · Computer Science 2021-12-23 Qi He , João Sedoc , Jordan Rodu

Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function…

Computation and Language · Computer Science 2026-05-25 Amit Dhurandhar , Vijil Chenthamarakshan , Dennis Wei , Tejaswini Pedapati , Karthikeyan Natesan Ramamurthy , Rahul Nair

Is it always necessary to compute tokens from shallow to deep layers in Transformers? The continued success of vanilla Transformers and their variants suggests an undoubted "yes". In this work, however, we attempt to break the depth-ordered…

Computation and Language · Computer Science 2024-07-10 Zhuocheng Gong , Ang Lv , Jian Guan , Junxi Yan , Wei Wu , Huishuai Zhang , Minlie Huang , Dongyan Zhao , Rui Yan

Error correction code is a major part of the communication physical layer, ensuring the reliable transfer of data over noisy channels. Recently, neural decoders were shown to outperform classical decoding techniques. However, the existing…

Machine Learning · Computer Science 2022-03-30 Yoni Choukroun , Lior Wolf

When the system is linear, why should learning be nonlinear? Linear dynamical systems, the analytical backbone of control theory, signal processing and circuit analysis, have exact closed-form solutions via the state transition matrix. Yet…

Machine Learning · Computer Science 2026-03-31 Shafayeth Jamil , Rehan Kapadia

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 introduce MixFunn, a novel neural network architecture designed to solve differential equations with enhanced precision, interpretability, and generalization capability. The architecture comprises two key components: the mixed-function…

Machine Learning · Computer Science 2025-03-31 Tiago de Souza Farias , Gubio Gomes de Lima , Jonas Maziero , Celso Jorge Villas-Boas