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 91 records · Page 5Linked to original sources

arXiv2025

DermETAS-SNA LLM: A Dermatology Focused Evolutionary Transformer Architecture Search with StackNet Augmented LLM Assistant

Our work introduces the DermETAS-SNA LLM Assistant that integrates Dermatology-focused Evolutionary Transformer Architecture Search with StackNet Augmented LLM. The assistant dynamically learns skin-disease classifiers and provides medically informed descriptions to facilitate clinician-patient interpretation. Contributions include: (1) Developed an ETAS framework on the SKINCON dataset to optimize a Vision Transformer (ViT) tailored for dermatological feature representation and then fine-tuned binary classifiers for each of the 23 skin disease categories in the DermNet dataset to enhance classification performance; (2) Designed a StackNet architecture that integrates multiple fine-tuned binary ViT classifiers to enhance predictive robustness and mitigate class imbalance issues; (3) Implemented a RAG pipeline, termed Diagnostic Explanation and Retrieval Model for Dermatology, which harnesses the capabilities of the Google Gemini 2.5 Pro LLM architecture to generate personalized, contextually informed diagnostic descriptions and explanations for patients, leveraging a repository of verified dermatological materials; (4) Performed extensive experimental evaluations on 23 skin disease categories to demonstrate performance increase, achieving an overall F1-score of 56.30% that surpasses SkinGPT-4 (48.51%) by a considerable margin, representing a performance increase of 16.06%; (5) Conducted a domain-expert evaluation, with eight licensed medical doctors, of the clinical responses generated by our AI assistant for seven dermatological conditions. Our results show a 92% agreement rate with the assessments provided by our AI assistant (6) Created a proof-of-concept prototype that fully integrates our DermETAS-SNA LLM into our AI assistant to demonstrate its practical feasibility for real-world clinical and educational applications.

eess.IV↗

arXiv2026

LALE: Lightweight-Transformer Architecture for Land-Cover Estimation

Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for global context, convolution for local detail, or compactness for efficiency. While hybrid approaches aim to capture both, they require architectural changes and encoder backbones with computational overhead, limiting efficiency and performance. We present LALE (Lightweight-transformer Architecture for Land-cover Estimation), an end-to-end remote sensing image segmentation architecture, that bifurcates its encoder by resolution: lightweight ConvMixer stages handle high-resolution local features, while transformer stages handle low-resolution global context, confining the quadratic cost of self-attention to deep, downsampled feature maps. An all-MLP multi-scale decoder, together with RMSNorm and StarReLU throughout, further reduces compute and parameter count. On the large-scale ARAS400k remote-sensing segmentation benchmark, LALE establishes a strong efficiency-performance trade-off against CNN, transformer, and hybrid baselines. Our smallest variant, (just 1.6M parameters), reaches within 2.6 F1 points of the best baseline (UPerNet) while using 4.5x fewer parameters, 7x less storage, 17x fewer GMACs, and delivering 1.8x higher throughput. The codebase for LALE is publicly available at https://github.com/caglarmert/LALE.

eess.IV↗

arXiv2025

Multi-Scale Transformer Architecture for Accurate Medical Image Classification

This study introduces an AI-driven skin lesion classification algorithm built on an enhanced Transformer architecture, addressing the challenges of accuracy and robustness in medical image analysis. By integrating a multi-scale feature fusion mechanism and refining the self-attention process, the model effectively extracts both global and local features, enhancing its ability to detect lesions with ambiguous boundaries and intricate structures. Performance evaluation on the ISIC 2017 dataset demonstrates that the improved Transformer surpasses established AI models, including ResNet50, VGG19, ResNext, and Vision Transformer, across key metrics such as accuracy, AUC, F1-Score, and Precision. Grad-CAM visualizations further highlight the interpretability of the model, showcasing strong alignment between the algorithm's focus areas and actual lesion sites. This research underscores the transformative potential of advanced AI models in medical imaging, paving the way for more accurate and reliable diagnostic tools. Future work will explore the scalability of this approach to broader medical imaging tasks and investigate the integration of multimodal data to enhance AI-driven diagnostic frameworks for intelligent healthcare.

cs.CV↗

arXiv2020

Hierarchical Attention Transformer Architecture For Syntactic Spell Correction

The attention mechanisms are playing a boosting role in advancements in sequence-to-sequence problems. Transformer architecture achieved new state of the art results in machine translation, and it's variants are since being introduced in several other sequence-to-sequence problems. Problems which involve a shared vocabulary, can benefit from the similar semantic and syntactic structure in the source and target sentences. With the motivation of building a reliable and fast post-processing textual module to assist all the text-related use cases in mobile phones, we take on the popular spell correction problem. In this paper, we propose multi encoder-single decoder variation of conventional transformer. Outputs from the three encoders with character level 1-gram, 2-grams and 3-grams inputs are attended in hierarchical fashion in the decoder. The context vectors from the encoders clubbed with self-attention amplify the n-gram properties at the character level and helps in accurate decoding. We demonstrate our model on spell correction dataset from Samsung Research, and report significant improvement of 0.11\%, 0.32\% and 0.69\% in character (CER), word (WER) and sentence (SER) error rates from existing state-of-the-art machine-translation architectures. Our architecture is also trains ~7.8 times faster, and is only about 1/3 in size from the next most accurate model.

cs.LG↗

arXiv2024

Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey

Transformer-based Large Language Models (LLMs) have been applied in diverse areas such as knowledge bases, human interfaces, and dynamic agents, and marking a stride towards achieving Artificial General Intelligence (AGI). However, current LLMs are predominantly pretrained on short text snippets, which compromises their effectiveness in processing the long-context prompts that are frequently encountered in practical scenarios. This article offers a comprehensive survey of the recent advancement in Transformer-based LLM architectures aimed at enhancing the long-context capabilities of LLMs throughout the entire model lifecycle, from pre-training through to inference. We first delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. We then provide a taxonomy and the landscape of upgrades on Transformer architecture to solve these problems. Afterwards, we provide an investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as optimization toolkits such as libraries, frameworks, and compilers to boost the efficacy of LLMs across different stages in runtime. Finally, we discuss the challenges and potential avenues for future research. A curated repository of relevant literature, continuously updated, is available at https://github.com/Strivin0311/long-llms-learning.

cs.CL↗

arXiv2024

Investigation of Hierarchical Spectral Vision Transformer Architecture for Classification of Hyperspectral Imagery

In the past three years, there has been significant interest in hyperspectral imagery (HSI) classification using vision Transformers for analysis of remotely sensed data. Previous research predominantly focused on the empirical integration of convolutional neural networks (CNNs) to augment the network's capability to extract local feature information. Yet, the theoretical justification for vision Transformers out-performing CNN architectures in HSI classification remains a question. To address this issue, a unified hierarchical spectral vision Transformer architecture, specifically tailored for HSI classification, is investigated. In this streamlined yet effective vision Transformer architecture, multiple mixer modules are strategically integrated separately. These include the CNN-mixer, which executes convolution operations; the spatial self-attention (SSA)-mixer and channel self-attention (CSA)-mixer, both of which are adaptations of classical self-attention blocks; and hybrid models such as the SSA+CNN-mixer and CSA+CNN-mixer, which merge convolution with self-attention operations. This integration facilitates the development of a broad spectrum of vision Transformer-based models tailored for HSI classification. In terms of the training process, a comprehensive analysis is performed, contrasting classical CNN models and vision Transformer-based counterparts, with particular attention to disturbance robustness and the distribution of the largest eigenvalue of the Hessian. From the evaluations conducted on various mixer models rooted in the unified architecture, it is concluded that the unique strength of vision Transformers can be attributed to their overarching architecture, rather than being exclusively reliant on individual multi-head self-attention (MSA) components.

cs.CV↗

arXiv2024

From Cognition to Computation: A Comparative Review of Human Attention and Transformer Architectures

Attention is a cornerstone of human cognition that facilitates the efficient extraction of information in everyday life. Recent developments in artificial intelligence like the Transformer architecture also incorporate the idea of attention in model designs. However, despite the shared fundamental principle of selectively attending to information, human attention and the Transformer model display notable differences, particularly in their capacity constraints, attention pathways, and intentional mechanisms. Our review aims to provide a comparative analysis of these mechanisms from a cognitive-functional perspective, thereby shedding light on several open research questions. The exploration encourages interdisciplinary efforts to derive insights from human attention mechanisms in the pursuit of developing more generalized artificial intelligence.

q-bio.OT↗

arXiv2020

Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring

The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018). For tasks that make pairwise comparisons between sequences, matching a given input with a corresponding label, two approaches are common: Cross-encoders performing full self-attention over the pair and Bi-encoders encoding the pair separately. The former often performs better, but is too slow for practical use. In this work, we develop a new transformer architecture, the Poly-encoder, that learns global rather than token level self-attention features. We perform a detailed comparison of all three approaches, including what pre-training and fine-tuning strategies work best. We show our models achieve state-of-the-art results on three existing tasks; that Poly-encoders are faster than Cross-encoders and more accurate than Bi-encoders; and that the best results are obtained by pre-training on large datasets similar to the downstream tasks.

cs.CL↗

arXiv2025

TART: Token-based Architecture Transformer for Neural Network Performance Prediction

In the realm of neural architecture design, achieving high performance is largely reliant on the manual expertise of researchers. Despite the emergence of Neural Architecture Search (NAS) as a promising technique for automating this process, current NAS methods still require human input to expand the search space and cannot generate new architectures. This paper explores the potential of Transformers in comprehending neural architectures and their performance, with the objective of establishing the foundation for utilizing Transformers to generate novel networks. We propose the Token-based Architecture Transformer (TART), which predicts neural network performance without the need to train candidate networks. TART attains state-of-the-art performance on the DeepNets-1M dataset for performance prediction tasks without edge information, indicating the potential of Transformers to aid in discovering novel and high-performing neural architectures.

cs.LG↗

arXiv2025

Local Attention Mechanism: Boosting the Transformer Architecture for Long-Sequence Time Series Forecasting

Transformers have become the leading choice in natural language processing over other deep learning architectures. This trend has also permeated the field of time series analysis, especially for long-horizon forecasting, showcasing promising results both in performance and running time. In this paper, we introduce Local Attention Mechanism (LAM), an efficient attention mechanism tailored for time series analysis. This mechanism exploits the continuity properties of time series to reduce the number of attention scores computed. We present an algorithm for implementing LAM in tensor algebra that runs in time and memory O(nlogn), significantly improving upon the O(n^2) time and memory complexity of traditional attention mechanisms. We also note the lack of proper datasets to evaluate long-horizon forecast models. Thus, we propose a novel set of datasets to improve the evaluation of models addressing long-horizon forecasting challenges. Our experimental analysis demonstrates that the vanilla transformer architecture magnified with LAM surpasses state-of-the-art models, including the vanilla attention mechanism. These results confirm the effectiveness of our approach and highlight a range of future challenges in long-sequence time series forecasting.

cs.LG↗

arXiv2026

Improving Financial Forecasting with a Synergistic LLM-Transformer Architecture: A Hybrid Approach to Stock Price Prediction

This study proposes a novel hybrid deep learning framework that integrates a Large Language Model (LLM) with a Transformer architecture for stock price forecasting. The research addresses a critical theoretical gap in existing approaches that empirically combine textual and numerical data without a formal understanding of their interaction mechanisms. We conceptualise a prompt-based LLM as a mathematically defined signal generator, capable of extracting directional market sentiment and an associated confidence score from financial news. These signals are then dynamically fused with structured historical price features through a noise-robust gating mechanism, enabling the Transformer to adaptively weigh semantic and quantitative information. Empirical evaluations demonstrate that the proposed Hybrid LLM-Transformer model significantly outperforms a Vanilla Transformer baseline, reducing the Root Mean Squared Error (RMSE) by 5.28% (p = 0.003). Moreover, ablation and robustness analyses confirm the model's stability under noisy conditions and its capacity to maintain interpretability through confidence-weighted attention. The findings provide both theoretical and empirical support for a paradigm shift from empirical observation to formalised modelling of LLM-Transformer interactions, paving the way toward explainable, noise-resilient, and semantically enriched financial forecasting systems.

econ.TH↗

arXiv2025

P-Transformer: A Prompt-based Multimodal Transformer Architecture For Medical Tabular Data

Medical tabular data, abundant in Electronic Health Records (EHRs), is a valuable resource for diverse medical tasks such as risk prediction. While deep learning approaches, particularly transformer-based models, have shown remarkable performance in tabular data prediction, there are still problems remaining for existing work to be effectively adapted into medical domain, such as ignoring unstructured free-texts and underutilizing the textual information in structured data. To address these issues, we propose PTransformer, a \underline{P}rompt-based multimodal \underline{Transformer} architecture designed specifically for medical tabular data. This framework consists of two critical components: a tabular cell embedding generator and a tabular transformer. The former efficiently encodes diverse modalities from both structured and unstructured tabular data into a harmonized language semantic space with the help of pre-trained sentence encoder and medical prompts. The latter integrates cell representations to generate patient embeddings for various medical tasks. In comprehensive experiments on two real-world datasets for three medical tasks, PTransformer demonstrated the improvements with 10.9%/11.0% on RMSE/MAE, 0.5%/2.2% on RMSE/MAE, and 1.6%/0.8% on BACC/AUROC compared to state-of-the-art (SOTA) baselines in predictability.

cs.CL↗

arXiv2023

Boosting the Performance of Transformer Architectures for Semantic Textual Similarity

Semantic textual similarity is the task of estimating the similarity between the meaning of two texts. In this paper, we fine-tune transformer architectures for semantic textual similarity on the Semantic Textual Similarity Benchmark by tuning the model partially and then end-to-end. We experiment with BERT, RoBERTa, and DeBERTaV3 cross-encoders by approaching the problem as a binary classification task or a regression task. We combine the outputs of the transformer models and use handmade features as inputs for boosting algorithms. Due to worse test set results coupled with improvements on the validation set, we experiment with different dataset splits to further investigate this occurrence. We also provide an error analysis, focused on the edges of the prediction range.

cs.CL↗

arXiv2022

Persistence Initialization: A novel adaptation of the Transformer architecture for Time Series Forecasting

Time series forecasting is an important problem, with many real world applications. Ensembles of deep neural networks have recently achieved impressive forecasting accuracy, but such large ensembles are impractical in many real world settings. Transformer models been successfully applied to a diverse set of challenging problems. We propose a novel adaptation of the original Transformer architecture focusing on the task of time series forecasting, called Persistence Initialization. The model is initialized as a naive persistence model by using a multiplicative gating mechanism combined with a residual skip connection. We use a decoder Transformer with ReZero normalization and Rotary positional encodings, but the adaptation is applicable to any auto-regressive neural network model. We evaluate our proposed architecture on the challenging M4 dataset, achieving competitive performance compared to ensemble based methods. We also compare against existing recently proposed Transformer models for time series forecasting, showing superior performance on the M4 dataset. Extensive ablation studies show that Persistence Initialization leads to better performance and faster convergence. As the size of the model increases, only the models with our proposed adaptation gain in performance. We also perform an additional ablation study to determine the importance of the choice of normalization and positional encoding, and find both the use of Rotary encodings and ReZero normalization to be essential for good forecasting performance.

cs.LG↗

arXiv2020

EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems

Understanding emotions and responding accordingly is one of the biggest challenges of dialog systems. This paper presents EmpTransfo, a multi-head Transformer architecture for creating an empathetic dialog system. EmpTransfo utilizes state-of-the-art pre-trained models (e.g., OpenAI-GPT) for language generation, though models with different sizes can be used. We show that utilizing the history of emotions and other metadata can improve the quality of generated conversations by the dialog system. Our experimental results using a challenging language corpus show that the proposed approach outperforms other models in terms of Hit@1 and PPL (Perplexity).

cs.CL↗

arXiv2024

LEFormer: A Hybrid CNN-Transformer Architecture for Accurate Lake Extraction from Remote Sensing Imagery

Lake extraction from remote sensing images is challenging due to the complex lake shapes and inherent data noises. Existing methods suffer from blurred segmentation boundaries and poor foreground modeling. This paper proposes a hybrid CNN-Transformer architecture, called LEFormer, for accurate lake extraction. LEFormer contains three main modules: CNN encoder, Transformer encoder, and cross-encoder fusion. The CNN encoder effectively recovers local spatial information and improves fine-scale details. Simultaneously, the Transformer encoder captures long-range dependencies between sequences of any length, allowing them to obtain global features and context information. The cross-encoder fusion module integrates the local and global features to improve mask prediction. Experimental results show that LEFormer consistently achieves state-of-the-art performance and efficiency on the Surface Water and the Qinghai-Tibet Plateau Lake datasets. Specifically, LEFormer achieves 90.86% and 97.42% mIoU on two datasets with a parameter count of 3.61M, respectively, while being 20 minor than the previous best lake extraction method. The source code is available at https://github.com/BastianChen/LEFormer.

cs.CV↗

arXiv2023

GeoViT: A Versatile Vision Transformer Architecture for Geospatial Image Analysis

Greenhouse gases are pivotal drivers of climate change, necessitating precise quantification and source identification to foster mitigation strategies. We introduce GeoViT, a compact vision transformer model adept in processing satellite imagery for multimodal segmentation, classification, and regression tasks targeting CO2 and NO2 emissions. Leveraging GeoViT, we attain superior accuracy in estimating power generation rates, fuel type, plume coverage for CO2, and high-resolution NO2 concentration mapping, surpassing previous state-of-the-art models while significantly reducing model size. GeoViT demonstrates the efficacy of vision transformer architectures in harnessing satellite-derived data for enhanced GHG emission insights, proving instrumental in advancing climate change monitoring and emission regulation efforts globally.

cs.CV↗

arXiv2025

ADAT: Time-Series-Aware Adaptive Transformer Architecture for Sign Language Translation

Current sign language machine translation systems rely on recognizing hand movements, facial expressions and body postures, and natural language processing, to convert signs into text. Recent approaches use Transformer architectures to model long-range dependencies via positional encoding. However, they lack accuracy in recognizing fine-grained, short-range temporal dependencies between gestures captured at high frame rates. Moreover, their high computational complexity leads to inefficient training. To mitigate these issues, we propose an Adaptive Transformer (ADAT), which incorporates components for enhanced feature extraction and adaptive feature weighting through a gating mechanism to emphasize contextually relevant features while reducing training overhead and maintaining translation accuracy. To evaluate ADAT, we introduce MedASL, the first public medical American Sign Language dataset. In sign-to-gloss-to-text experiments, ADAT outperforms the encoder-decoder transformer, improving BLEU-4 accuracy by 0.1% while reducing training time by 14.33% on PHOENIX14T and 3.24% on MedASL. In sign-to-text experiments, it improves accuracy by 8.7% and reduces training time by 2.8% on PHOENIX14T and achieves 4.7% higher accuracy and 7.17% faster training on MedASL. Compared to encoder-only and decoder-only baselines in sign-to-text, ADAT is at least 6.8% more accurate despite being up to 12.1% slower due to its dual-stream structure.

cs.AI↗