SEARCH · Searcharxiv

Results for “transformer architecture”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7Linked to original sources

arXiv2024

Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks

Transformer neural networks are increasingly replacing prior architectures in a wide range of applications in different data modalities. The increasing size and computational demands of fine-tuning large pre-trained transformer neural networks pose significant challenges for the widespread adoption of these models for applications that demand on-edge computing. To tackle this challenge, continual learning (CL) emerges as a solution by facilitating the transfer of knowledge across tasks that arrive sequentially for an autonomously learning agent. However, current CL methods mainly focus on learning tasks that are exclusively vision-based or language-based. We propose a transformer-based CL framework focusing on learning tasks that involve both vision and language, known as Vision-and-Language (VaL) tasks. Due to the success of transformers in other modalities, our architecture has the potential to be used in multimodal learning settings. In our framework, we benefit from introducing extra parameters to a base transformer to specialize the network for each task. As a result, we enable dynamic model expansion to learn several tasks in a sequence. We also use knowledge distillation to benefit from relevant past experiences to learn the current task more efficiently. Our proposed method, Task Attentive Multimodal Continual Learning (TAM-CL), allows for the exchange of information between tasks while mitigating the problem of catastrophic forgetting. Notably, our approach is scalable, incurring minimal memory and time overhead. TAM-CL achieves state-of-the-art (SOTA) performance on challenging multimodal tasks

cs.CV↗

arXiv2022

Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting

Time series data is ubiquitous in research as well as in a wide variety of industrial applications. Effectively analyzing the available historical data and providing insights into the far future allows us to make effective decisions. Recent research has witnessed the superior performance of transformer-based architectures, especially in the regime of far horizon time series forecasting. However, the current state of the art sparse Transformer architectures fail to couple down- and upsampling procedures to produce outputs in a similar resolution as the input. We propose the Yformer model, based on a novel Y-shaped encoder-decoder architecture that (1) uses direct connection from the downscaled encoder layer to the corresponding upsampled decoder layer in a U-Net inspired architecture, (2) Combines the downscaling/upsampling with sparse attention to capture long-range effects, and (3) stabilizes the encoder-decoder stacks with the addition of an auxiliary reconstruction loss. Extensive experiments have been conducted with relevant baselines on four benchmark datasets, demonstrating an average improvement of 19.82, 18.41 percentage MSE and 13.62, 11.85 percentage MAE in comparison to the current state of the art for the univariate and the multivariate settings respectively.

cs.LG↗

arXiv2026

Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis

Stock market prediction presents considerable challenges for investors, financial institutions, and policymakers operating in complex market environments characterized by noise, non-stationarity, and behavioral dynamics. Traditional forecasting methods, including fundamental analysis and technical indicators, often fail to capture the intricate patterns and cross-sectional dependencies inherent in financial markets. This paper presents an integrated framework combining a node transformer architecture with BERT-based sentiment analysis for stock price forecasting. The proposed model represents the stock market as a graph structure where individual stocks form nodes and edges capture relationships including sectoral affiliations, correlated price movements, and supply chain connections. A fine-tuned BERT model extracts sentiment information from social media posts and combines it with quantitative market features through attention-based fusion mechanisms. The node transformer processes historical market data while capturing both temporal evolution and cross-sectional dependencies among stocks. Experiments conducted on 20 S&P 500 stocks spanning January 1982 to March 2025 demonstrate that the integrated model achieves a mean absolute percentage error (MAPE) of 0.80% for one-day-ahead predictions, compared to 1.20% for ARIMA and 1.00% for LSTM. The inclusion of sentiment analysis reduces prediction error by 10% overall and 25% during earnings announcements, while the graph-based architecture contributes an additional 15% improvement by capturing inter-stock dependencies. Directional accuracy reaches 65% for one-day forecasts. Statistical validation through paired t-tests confirms the significance of these improvements (p < 0.05 for all comparisons). The model maintains lower error during high-volatility periods, achieving MAPE of 1.50% while baseline models range from 1.60% to 2.10%.

cs.LG↗

arXiv2025

ChromaFormer: A Scalable and Accurate Transformer Architecture for Land Cover Classification

Remote sensing imagery from systems such as Sentinel provides full coverage of the Earth's surface at around 10-meter resolution. The remote sensing community has transitioned to extensive use of deep learning models due to their high performance on benchmarks such as the UCMerced and ISPRS Vaihingen datasets. Convolutional models such as UNet and ResNet variations are commonly employed for remote sensing but typically only accept three channels, as they were developed for RGB imagery, while satellite systems provide more than ten. Recently, several transformer architectures have been proposed for remote sensing, but they have not been extensively benchmarked and are typically used on small datasets such as Salinas Valley. Meanwhile, it is becoming feasible to obtain dense spatial land-use labels for entire first-level administrative divisions of some countries. Scaling law observations suggest that substantially larger multi-spectral transformer models could provide a significant leap in remote sensing performance in these settings. In this work, we propose ChromaFormer, a family of multi-spectral transformer models, which we evaluate across orders of magnitude differences in model parameters to assess their performance and scaling effectiveness on a densely labeled imagery dataset of Flanders, Belgium, covering more than 13,500 km^2 and containing 15 classes. We propose a novel multi-spectral attention strategy and demonstrate its effectiveness through ablations. Furthermore, we show that models many orders of magnitude larger than conventional architectures, such as UNet, lead to substantial accuracy improvements: a UNet++ model with 23M parameters achieves less than 65% accuracy, while a multi-spectral transformer with 655M parameters achieves over 95% accuracy on the Biological Valuation Map of Flanders.

cs.CV↗

arXiv2022

T4PdM: a Deep Neural Network based on the Transformer Architecture for Fault Diagnosis of Rotating Machinery

Deep learning and big data algorithms have become widely used in industrial applications to optimize several tasks in many complex systems. Particularly, deep learning model for diagnosing and prognosing machinery health has leveraged predictive maintenance (PdM) to be more accurate and reliable in decision making, in this way avoiding unnecessary interventions, machinery accidents, and environment catastrophes. Recently, Transformer Neural Networks have gained notoriety and have been increasingly the favorite choice for Natural Language Processing (NLP) tasks. Thus, given their recent major achievements in NLP, this paper proposes the development of an automatic fault classifier model for predictive maintenance based on a modified version of the Transformer architecture, namely T4PdM, to identify multiple types of faults in rotating machinery. Experimental results are developed and presented for the MaFaulDa and CWRU databases. T4PdM was able to achieve an overall accuracy of 99.98% and 98% for both datasets, respectively. In addition, the performance of the proposed model is compared to other previously published works. It has demonstrated the superiority of the model in detecting and classifying faults in rotating industrial machinery. Therefore, the proposed Transformer-based model can improve the performance of machinery fault analysis and diagnostic processes and leverage companies to a new era of the Industry 4.0. In addition, this methodology can be adapted to any other task of time series classification.

cs.AI↗

arXiv2025

Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing Transformer models while providing desirable theoretical guarantees, including generalization and robustness. Our framework is designed to be plug-and-play, enabling seamless integration with established Transformer models and requiring only slight changes to the implementation. We conduct seven extensive experiments on tasks motivated by text generation, sentiment analysis, image classification, and point cloud classification. Experimental results show that the framework improves the test performance of the baselines, while being more parameter-efficient. On character-level text generation with nanoGPT, our framework achieves a 46% reduction in final test loss while using 42% fewer parameters. On GPT-2, our framework achieves a 9.3% reduction in final test loss, demonstrating scalability to larger models. To the best of our knowledge, this is the first work that applies optimal control theory to both the training and architecture of Transformers. It offers a new foundation for systematic, theory-driven improvements and moves beyond costly trial-and-error approaches.

cs.LG↗

arXiv2026

Astra: Efficient Transformer Architecture and Contrastive Dynamics Learning for Embodied Instruction Following

Vision-language-action models have gained significant attention for their ability to model multimodal sequences in embodied instruction following tasks. However, most existing models rely on causal attention, which we find suboptimal for processing sequences composed of interleaved segments from different modalities. In this paper, we introduce Astra, a novel Transformer architecture featuring trajectory attention and learnable action queries, designed to efficiently process segmented multimodal trajectories and predict actions for imitation learning. Furthermore, we propose a contrastive dynamics learning objective to enhance the model's understanding of environment dynamics and multimodal alignment, complementing the primary behavior cloning objective. Through extensive experiments on three large-scale robot manipulation benchmarks, Astra demonstrates substantial performance improvements over previous models.

cs.RO↗

arXiv2024

1DFormer: a Transformer Architecture Learning 1D Landmark Representations for Facial Landmark Tracking

Recently, heatmap regression methods based on 1D landmark representations have shown prominent performance on locating facial landmarks. However, previous methods ignored to make deep explorations on the good potentials of 1D landmark representations for sequential and structural modeling of multiple landmarks to track facial landmarks. To address this limitation, we propose a Transformer architecture, namely 1DFormer, which learns informative 1D landmark representations by capturing the dynamic and the geometric patterns of landmarks via token communications in both temporal and spatial dimensions for facial landmark tracking. For temporal modeling, we propose a recurrent token mixing mechanism, an axis-landmark-positional embedding mechanism, as well as a confidence-enhanced multi-head attention mechanism to adaptively and robustly embed long-term landmark dynamics into their 1D representations; for structure modeling, we design intra-group and inter-group structure modeling mechanisms to encode the component-level as well as global-level facial structure patterns as a refinement for the 1D representations of landmarks through token communications in the spatial dimension via 1D convolutional layers. Experimental results on the 300VW and the TF databases show that 1DFormer successfully models the long-range sequential patterns as well as the inherent facial structures to learn informative 1D representations of landmark sequences, and achieves state-of-the-art performance on facial landmark tracking.

cs.CV↗

arXiv2020

Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture

Sparse models require less memory for storage and enable a faster inference by reducing the necessary number of FLOPs. This is relevant both for time-critical and on-device computations using neural networks. The stabilized lottery ticket hypothesis states that networks can be pruned after none or few training iterations, using a mask computed based on the unpruned converged model. On the transformer architecture and the WMT 2014 English-to-German and English-to-French tasks, we show that stabilized lottery ticket pruning performs similar to magnitude pruning for sparsity levels of up to 85%, and propose a new combination of pruning techniques that outperforms all other techniques for even higher levels of sparsity. Furthermore, we confirm that the parameter's initial sign and not its specific value is the primary factor for successful training, and show that magnitude pruning could be used to find winning lottery tickets.

cs.LG↗

arXiv2025

Small transformer architectures for task switching

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional approaches, such as multi-layer perceptrons or recurrent networks. We examine this problem in the context of 'task switching'. In this framework models work on ongoing token sequences with the current task being determined by stochastically interspersed control tokens. We show that standard transformers cannot solve a basic task switching reference model based on finite domain arithmetics which contains subtasks dedicated to increment / addition / reverse copy / context (IARC). We show that transformers, long short-term memory recurrent networks (LSTM), and plain multi-layer perceptrons (MLPs) achieve similar, but only modest prediction accuracies. We enlarge our comparative study by including an extension of the standard transformer architecture to its non-translational invariant counterpart, the cisformer, and an alternative attention mechanism, extensive attention. A combination of the latter is found to be the only model able to achieve considerable performance levels, of around 95%. Our results indicate that the workings of attention can be understood better, and even improved, when comparing qualitatively different formulations in task-switching settings.

cs.LG↗

arXiv2021

MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding (NLU) domain has been limited, due to the difficulty of interpolating text directly in the input space. In this study, we propose MixUp methods at the Input, Manifold, and sentence embedding levels for the transformer architecture, and apply them to finetune the BERT model for a diverse set of NLU tasks. We find that MixUp can improve model performance, as well as reduce test loss and model calibration error by up to 50%.

cs.CL↗

arXiv2024

Transfer Learning and Transformer Architecture for Financial Sentiment Analysis

Financial sentiment analysis allows financial institutions like Banks and Insurance Companies to better manage the credit scoring of their customers in a better way. Financial domain uses specialized mechanisms which makes sentiment analysis difficult. In this paper, we propose a pre-trained language model which can help to solve this problem with fewer labelled data. We extend on the principles of Transfer learning and Transformation architecture principles and also take into consideration recent outbreak of pandemics like COVID. We apply the sentiment analysis to two different sets of data. We also take smaller training set and fine tune the same as part of the model.

cs.CL↗

arXiv2025

Set Transformer Architectures and Synthetic Data Generation for Flow-Guided Nanoscale Localization

Flow-guided Localization (FGL) enables the identification of spatial regions within the human body that contain an event of diagnostic interest. FGL does that by leveraging the passive movement of energy-constrained nanodevices circulating through the bloodstream. Existing FGL solutions rely on graph models with fixed topologies or handcrafted features, which limit their adaptability to anatomical variability and hinder scalability. In this work, we explore the use of Set Transformer architectures to address these limitations. Our formulation treats nanodevices' circulation time reports as unordered sets, enabling permutation-invariant, variable-length input processing without relying on spatial priors. To improve robustness under data scarcity and class imbalance, we integrate synthetic data generation via deep generative models, including CGAN, WGAN, WGAN-GP, and CVAE. These models are trained to replicate realistic circulation time distributions conditioned on vascular region labels, and are used to augment the training data. Our results show that the Set Transformer achieves comparable classification accuracy compared to Graph Neural Networks (GNN) baselines, while simultaneously providing by-design improved generalization to anatomical variability. The findings highlight the potential of permutation-invariant models and synthetic augmentation for robust and scalable nanoscale localization.

cs.ET↗

arXiv2026

Explainable Flood Segmentation on Sentinel-1 SAR1 Imagery Using CNN and Transformer Architectures

Rapid and accurate flood prediction is essential for disaster response and mitigation planning. Synthetic Aperture Radar (SAR) sensors in satellites are well-suited for this purpose because they operate independently of weather and daylight conditions. Although SAR-based data enable all-weather flood monitoring, distinguishing flooded land from permanent water remains a significant challenge, particularly when flooding is defined strictly as inundated land. This study provides a comprehensive comparison of convolutional neural network (CNN) and vision transformer architectures for multi-class flood segmentation using Sentinel-1 SAR imagery, specifically trained to separate flooded land from permanent water bodies and land. Three state-of-the-art (SOTA)CNN-based models, U-Net, U-Net++, and DeepLabV3 with ResNet-34 backbone, and three SegFormer variants (b0,b1,b2) were evaluated in two benchmark datasets, the ETCI NASA dataset and SenFloods11, using scene-based data splits to ensure a realistic assessment of spatial generalization. The results demonstrate that SegFormer-b2 significantly outperforms the U-Net baseline on the ETCI dataset (higher flood IoU across all 7 test scenes in the Wilcoxon signed-rank test), while after fine-tuning on Sen1Floods11, the advantage narrows to within the range of scene variability and is concentrated in spatially fragmented flood events. The study includes both qualitative and quantitative explainability techniques to visually comprehend model decisions and systematically assess prediction reliability. Qualitative analysis reveals that SegFormer-b2 produces more spatially coherent Grad-CAM activations focused on flood-relevant features, while U-Net generates more informative uncertainty estimates along flood boundaries.

cs.CV↗

arXiv2025

Self-Attention as Distributional Projection: A Unified Interpretation of Transformer Architecture

This paper presents a mathematical interpretation of self-attention by connecting it to distributional semantics principles. We show that self-attention emerges from projecting corpus-level co-occurrence statistics into sequence context. Starting from the co-occurrence matrix underlying GloVe embeddings, we demonstrate how the projection naturally captures contextual influence, with the query-key-value mechanism arising as the natural asymmetric extension for modeling directional relationships. Positional encodings and multi-head attention then follow as structured refinements of this same projection principle. Our analysis demonstrates that the Transformer architecture's particular algebraic form follows from these projection principles rather than being an arbitrary design choice.

cs.LG↗

arXiv2024

STeInFormer: Spatial-Temporal Interaction Transformer Architecture for Remote Sensing Change Detection

Convolutional neural networks and attention mechanisms have greatly benefited remote sensing change detection (RSCD) because of their outstanding discriminative ability. Existent RSCD methods often follow a paradigm of using a non-interactive Siamese neural network for multi-temporal feature extraction and change detection heads for feature fusion and change representation. However, this paradigm lacks the contemplation of the characteristics of RSCD in temporal and spatial dimensions, and causes the drawback on spatial-temporal interaction that hinders high-quality feature extraction. To address this problem, we present STeInFormer, a spatial-temporal interaction Transformer architecture for multi-temporal feature extraction, which is the first general backbone network specifically designed for RSCD. In addition, we propose a parameter-free multi-frequency token mixer to integrate frequency-domain features that provide spectral information for RSCD. Experimental results on three datasets validate the effectiveness of the proposed method, which can outperform the state-of-the-art methods and achieve the most satisfactory efficiency-accuracy trade-off. Code is available at https://github.com/xwmaxwma/rschange.

cs.CV↗

arXiv2025

Batch Transformer Architecture: Case of Synthetic Image Generation for Emotion Expression Facial Recognition

A novel Transformer variation architecture is proposed in the implicit sparse style. Unlike "traditional" Transformers, instead of attention to sequential or batch entities in their entirety of whole dimensionality, in the proposed Batch Transformers, attention to the "important" dimensions (primary components) is implemented. In such a way, the "important" dimensions or feature selection allows for a significant reduction of the bottleneck size in the encoder-decoder ANN architectures. The proposed architecture is tested on the synthetic image generation for the face recognition task in the case of the makeup and occlusion data set, allowing for increased variability of the limited original data set.

cs.CV↗

arXiv2024

From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation Systems: Survey, Taxonomy and Performance Evaluation

With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end translation system, from sign to gloss to text and vice-versa. There has been a wealth of research on machine translations and related reviews. However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. We also present the requirements of a real-time Quality-of-Service sign language ma-chine translation system underpinned by accurate deep learning algorithms. We propose future research directions for sign language translation systems.

cs.AI↗