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 361 records · Page 20Linked to original sources

arXiv2020

Resolving the Scope of Speculation and Negation using Transformer-Based Architectures

Speculation is a naturally occurring phenomena in textual data, forming an integral component of many systems, especially in the biomedical information retrieval domain. Previous work addressing cue detection and scope resolution (the two subtasks of speculation detection) have ranged from rule-based systems to deep learning-based approaches. In this paper, we apply three popular transformer-based architectures, BERT, XLNet and RoBERTa to this task, on two publicly available datasets, BioScope Corpus and SFU Review Corpus, reporting substantial improvements over previously reported results (by at least 0.29 F1 points on cue detection and 4.27 F1 points on scope resolution). We also experiment with joint training of the model on multiple datasets, which outperforms the single dataset training approach by a good margin. We observe that XLNet consistently outperforms BERT and RoBERTa, contrary to results on other benchmark datasets. To confirm this observation, we apply XLNet and RoBERTa to negation detection and scope resolution, reporting state-of-the-art results on negation scope resolution for the BioScope Corpus (increase of 3.16 F1 points on the BioScope Full Papers, 0.06 F1 points on the BioScope Abstracts) and the SFU Review Corpus (increase of 0.3 F1 points).

cs.CL↗

arXiv2021

Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillation

We present a novel large-context end-to-end automatic speech recognition (E2E-ASR) model and its effective training method based on knowledge distillation. Common E2E-ASR models have mainly focused on utterance-level processing in which each utterance is independently transcribed. On the other hand, large-context E2E-ASR models, which take into account long-range sequential contexts beyond utterance boundaries, well handle a sequence of utterances such as discourses and conversations. However, the transformer architecture, which has recently achieved state-of-the-art ASR performance among utterance-level ASR systems, has not yet been introduced into the large-context ASR systems. We can expect that the transformer architecture can be leveraged for effectively capturing not only input speech contexts but also long-range sequential contexts beyond utterance boundaries. Therefore, this paper proposes a hierarchical transformer-based large-context E2E-ASR model that combines the transformer architecture with hierarchical encoder-decoder based large-context modeling. In addition, in order to enable the proposed model to use long-range sequential contexts, we also propose a large-context knowledge distillation that distills the knowledge from a pre-trained large-context language model in the training phase. We evaluate the effectiveness of the proposed model and proposed training method on Japanese discourse ASR tasks.

cs.CL↗

arXiv2023

Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation

Referring Video Object Segmentation (RVOS) requires segmenting the object in video referred by a natural language query. Existing methods mainly rely on sophisticated pipelines to tackle such cross-modal task, and do not explicitly model the object-level spatial context which plays an important role in locating the referred object. Therefore, we propose an end-to-end RVOS framework completely built upon transformers, termed \textit{Fully Transformer-Equipped Architecture} (FTEA), which treats the RVOS task as a mask sequence learning problem and regards all the objects in video as candidate objects. Given a video clip with a text query, the visual-textual features are yielded by encoder, while the corresponding pixel-level and word-level features are aligned in terms of semantic similarity. To capture the object-level spatial context, we have developed the Stacked Transformer, which individually characterizes the visual appearance of each candidate object, whose feature map is decoded to the binary mask sequence in order directly. Finally, the model finds the best matching between mask sequence and text query. In addition, to diversify the generated masks for candidate objects, we impose a diversity loss on the model for capturing more accurate mask of the referred object. Empirical studies have shown the superiority of the proposed method on three benchmarks, e.g., FETA achieves 45.1% and 38.7% in terms of mAP on A2D Sentences (3782 videos) and J-HMDB Sentences (928 videos), respectively; it achieves 56.6% in terms of $\mathcal{J\&F}$ on Ref-YouTube-VOS (3975 videos and 7451 objects). Particularly, compared to the best candidate method, it has a gain of 2.1% and 3.2% in terms of P$@$0.5 on the former two, respectively, while it has a gain of 2.9% in terms of $\mathcal{J}$ on the latter one.

cs.CV↗

arXiv2023

EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms

Automated design of efficient transformer models has recently attracted significant attention from industry and academia. However, most works only focus on certain metrics while searching for the best-performing transformer architecture. Furthermore, running traditional, complex, and large transformer models on low-compute edge platforms is a challenging problem. In this work, we propose a framework, called ProTran, to profile the hardware performance measures for a design space of transformer architectures and a diverse set of edge devices. We use this profiler in conjunction with the proposed co-design technique to obtain the best-performing models that have high accuracy on the given task and minimize latency, energy consumption, and peak power draw to enable edge deployment. We refer to our framework for co-optimizing accuracy and hardware performance measures as EdgeTran. It searches for the best transformer model and edge device pair. Finally, we propose GPTran, a multi-stage block-level grow-and-prune post-processing step that further improves accuracy in a hardware-aware manner. The obtained transformer model is 2.8$\times$ smaller and has a 0.8% higher GLUE score than the baseline (BERT-Base). Inference with it on the selected edge device enables 15.0% lower latency, 10.0$\times$ lower energy, and 10.8$\times$ lower peak power draw compared to an off-the-shelf GPU.

cs.LG↗

arXiv2024

Transformer-based Federated Learning for Multi-Label Remote Sensing Image Classification

Federated learning (FL) aims to collaboratively learn deep learning model parameters from decentralized data archives (i.e., clients) without accessing training data on clients. However, the training data across clients might be not independent and identically distributed (non-IID), which may result in difficulty in achieving optimal model convergence. In this work, we investigate the capability of state-of-the-art transformer architectures (which are MLP-Mixer, ConvMixer, PoolFormer) to address the challenges related to non-IID training data across various clients in the context of FL for multi-label classification (MLC) problems in remote sensing (RS). The considered transformer architectures are compared among themselves and with the ResNet-50 architecture in terms of their: 1) robustness to training data heterogeneity; 2) local training complexity; and 3) aggregation complexity under different non-IID levels. The experimental results obtained on the BigEarthNet-S2 benchmark archive demonstrate that the considered architectures increase the generalization ability with the cost of higher local training and aggregation complexities. On the basis of our analysis, some guidelines are derived for a proper selection of transformer architecture in the context of FL for RS MLC. The code of this work is publicly available at https://git.tu-berlin.de/rsim/FL-Transformer.

cs.CV↗

arXiv2026

ITGPT: A Transformer Based Architecture for the Generation of Dance Dance Revolution and In the Groove Charts

Dance Dance Revolution and In the Groove are rhythm games consisting of songs and accompanying choreography, referred to as charts. Players press arrows on a device referred to as a dance pad in time with steps determined by the song's chart. The process of manual chart generation is timestaking and difficult, motivating interest in automation. We propose ITGPT, a new transformer based architecture for the generation of DDR/ITG charts, and demonstrate significant improvements to generation accuracy and computational cost in comparison to predecessor work.

cs.SD↗

arXiv2025

TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba

Transformer-based architectures have become the backbone of both uni-modal and multi-modal foundation models, largely due to their scalability via attention mechanisms, resulting in a rich ecosystem of publicly available pre-trained models such as LLaVA, CLIP, and DeiT, etc. In parallel, emerging sub-quadratic architectures like Mamba offer promising efficiency gains by enabling global context modeling with linear complexity. However, training these architectures from scratch remains resource-intensive (e.g., in terms of data and time). Motivated by this challenge, we explore a cross-architecture knowledge transfer paradigm, termed TransMamba, that facilitates the reuse of Transformer pre-trained knowledge. We propose a two-stage framework to accelerate the training of Mamba-based models, ensuring their effectiveness across both uni-modal and multi-modal tasks. The first stage leverages pre-trained Transformer models to initialize critical components of the Mamba architecture. To bridge architectural and dimensional gaps, we develop a selective weight subcloning strategy and a layered initialization scheme that prioritizes the early $n$ layers. Building on this initialization, the second stage introduces an adaptive multi-directional knowledge distillation method. This mechanism employs layer-wise adaptive scaling factors to align Mamba representations with their Transformer counterparts, while accommodating the scanning order variations inherent to multi-modal Mamba architectures. Despite operating with a reduced training dataset and a more compact model architecture, TransMamba consistently outperforms baseline approaches across diverse mamba-based backbones (e.g., PlainMamba, Vmamba, ViM and VideoMamba) and downstream tasks (e.g., image classification, visual question answering, text-video retrieval and multimodal reasoning). All code and implementation details will be released.

cs.CV↗

arXiv2024

Enhancing Automatic Keyphrase Labelling with Text-to-Text Transfer Transformer (T5) Architecture: A Framework for Keyphrase Generation and Filtering

Automatic keyphrase labelling stands for the ability of models to retrieve words or short phrases that adequately describe documents' content. Previous work has put much effort into exploring extractive techniques to address this task; however, these methods cannot produce keyphrases not found in the text. Given this limitation, keyphrase generation approaches have arisen lately. This paper presents a keyphrase generation model based on the Text-to-Text Transfer Transformer (T5) architecture. Having a document's title and abstract as input, we learn a T5 model to generate keyphrases which adequately define its content. We name this model docT5keywords. We not only perform the classic inference approach, where the output sequence is directly selected as the predicted values, but we also report results from a majority voting approach. In this approach, multiple sequences are generated, and the keyphrases are ranked based on their frequency of occurrence across these sequences. Along with this model, we present a novel keyphrase filtering technique based on the T5 architecture. We train a T5 model to learn whether a given keyphrase is relevant to a document. We devise two evaluation methodologies to prove our model's capability to filter inadequate keyphrases. First, we perform a binary evaluation where our model has to predict if a keyphrase is relevant for a given document. Second, we filter the predicted keyphrases by several AKG models and check if the evaluation scores are improved. Experimental results demonstrate that our keyphrase generation model significantly outperforms all the baselines, with gains exceeding 100\% in some cases. The proposed filtering technique also achieves near-perfect accuracy in eliminating false positives across all datasets.

cs.IR↗

arXiv2025

Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph

Millions of individuals worldwide are affected by deafness and hearing impairment. Sign language serves as a sophisticated means of communication for the deaf and hard of hearing. However, in societies that prioritize spoken languages, sign language often faces underestimation, leading to communication barriers and social exclusion. The Continuous Bangla Sign Language Translation project aims to address this gap by enhancing translation methods. While recent approaches leverage transformer architecture for state-of-the-art results, our method integrates graph-based methods with the transformer architecture. This fusion, combining transformer and STGCN-LSTM architectures, proves more effective in gloss-free translation. Our contributions include architectural fusion, exploring various fusion strategies, and achieving a new state-of-the-art performance on diverse sign language datasets, namely RWTH-PHOENIX-2014T, CSL-Daily, How2Sign, and BornilDB v1.0. Our approach demonstrates superior performance compared to current translation outcomes across all datasets, showcasing notable improvements of BLEU-4 scores of 4.01, 2.07, and 0.5, surpassing those of GASLT, GASLT and slt_how2sign in RWTH-PHOENIX-2014T, CSL-Daily, and How2Sign, respectively. Also, we introduce benchmarking on the BornilDB v1.0 dataset for the first time. Our method sets a benchmark for future research, emphasizing the importance of gloss-free translation to improve communication accessibility for the deaf and hard of hearing.

cs.CL↗

arXiv2023

LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation

This paper presents LightLM, a lightweight Transformer-based language model for generative recommendation. While Transformer-based generative modeling has gained importance in various AI sub-fields such as NLP and vision, generative recommendation is still in its infancy due to its unique demand on personalized generative modeling. Existing works on generative recommendation often use NLP-oriented Transformer architectures such as T5, GPT, LLaMA and M6, which are heavy-weight and are not specifically designed for recommendation tasks. LightLM tackles the issue by introducing a light-weight deep and narrow Transformer architecture, which is specifically tailored for direct generation of recommendation items. This structure is especially apt for straightforward generative recommendation and stems from the observation that language model does not have to be too wide for this task, as the input predominantly consists of short tokens that are well-suited for the model's capacity. We also show that our devised user and item ID indexing methods, i.e., Spectral Collaborative Indexing (SCI) and Graph Collaborative Indexing (GCI), enables the deep and narrow Transformer architecture to outperform large-scale language models for recommendation. Besides, to address the hallucination problem of generating items as output, we propose the constrained generation process for generative recommenders. Experiments on real-world datasets show that LightLM outperforms various competitive baselines in terms of both recommendation accuracy and efficiency. The code can be found at https://github.com/dongyuanjushi/LightLM.

cs.IR↗

arXiv2025

METHOD: Modular Efficient Transformer for Health Outcome Discovery

Recent advances in transformer architectures have revolutionised natural language processing, but their application to healthcare domains presents unique challenges. Patient timelines are characterised by irregular sampling, variable temporal dependencies, and complex contextual relationships that differ substantially from traditional language tasks. This paper introduces \METHOD~(Modular Efficient Transformer for Health Outcome Discovery), a novel transformer architecture specifically designed to address the challenges of clinical sequence modelling in electronic health records. \METHOD~integrates three key innovations: (1) a patient-aware attention mechanism that prevents information leakage whilst enabling efficient batch processing; (2) an adaptive sliding window attention scheme that captures multi-scale temporal dependencies; and (3) a U-Net inspired architecture with dynamic skip connections for effective long sequence processing. Evaluations on the MIMIC-IV database demonstrate that \METHOD~consistently outperforms the state-of-the-art \ETHOS~model, particularly in predicting high-severity cases that require urgent clinical intervention. \METHOD~exhibits stable performance across varying inference lengths, a crucial feature for clinical deployment where patient histories vary significantly in length. Analysis of learned embeddings reveals that \METHOD~better preserves clinical hierarchies and relationships between medical concepts. These results suggest that \METHOD~represents a significant advancement in transformer architectures optimised for healthcare applications, providing more accurate and clinically relevant predictions whilst maintaining computational efficiency.

cs.CL↗

arXiv2020

Modern Hopfield Networks and Attention for Immune Repertoire Classification

A central mechanism in machine learning is to identify, store, and recognize patterns. How to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more recent transformer architectures. We show that the attention mechanism of transformer architectures is actually the update rule of modern Hopfield networks that can store exponentially many patterns. We exploit this high storage capacity of modern Hopfield networks to solve a challenging multiple instance learning (MIL) problem in computational biology: immune repertoire classification. Accurate and interpretable machine learning methods solving this problem could pave the way towards new vaccines and therapies, which is currently a very relevant research topic intensified by the COVID-19 crisis. Immune repertoire classification based on the vast number of immunosequences of an individual is a MIL problem with an unprecedentedly massive number of instances, two orders of magnitude larger than currently considered problems, and with an extremely low witness rate. In this work, we present our novel method DeepRC that integrates transformer-like attention, or equivalently modern Hopfield networks, into deep learning architectures for massive MIL such as immune repertoire classification. We demonstrate that DeepRC outperforms all other methods with respect to predictive performance on large-scale experiments, including simulated and real-world virus infection data, and enables the extraction of sequence motifs that are connected to a given disease class. Source code and datasets: https://github.com/ml-jku/DeepRC

cs.LG↗

arXiv2024

ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models

Planning is a crucial element of both human intelligence and contemporary large language models (LLMs). In this paper, we initiate a theoretical investigation into the emergence of planning capabilities in Transformer-based LLMs via their next-word prediction mechanisms. We model planning as a network path-finding task, where the objective is to generate a valid path from a specified source node to a designated target node. Our mathematical characterization shows that Transformer architectures can execute path-finding by embedding the adjacency and reachability matrices within their weights. Furthermore, our theoretical analysis of gradient-based learning dynamics reveals that LLMs can learn both the adjacency and a limited form of the reachability matrices. These theoretical insights are then validated through experiments, which demonstrate that Transformer architectures indeed learn the adjacency and an incomplete reachability matrices, consistent with our theoretical predictions. When applying our methodology to the real-world planning benchmark Blocksworld, our observations remain consistent. Additionally, our analyses uncover a fundamental limitation of current Transformer architectures in path-finding: these architectures cannot identify reachability relationships through transitivity, which leads to failures in generating paths when concatenation is required. These findings provide new insights into how the internal mechanisms of autoregressive learning facilitate intelligent planning and deepen our understanding of how future LLMs might achieve more advanced and general planning-and-reasoning capabilities across diverse applications.

cs.LG↗

arXiv2023

TopoMask: Instance-Mask-Based Formulation for the Road Topology Problem via Transformer-Based Architecture

Driving scene understanding task involves detecting static elements such as lanes, traffic signs, and traffic lights, and their relationships with each other. To facilitate the development of comprehensive scene understanding solutions using multiple camera views, a new dataset called Road Genome (OpenLane-V2) has been released. This dataset allows for the exploration of complex road connections and situations where lane markings may be absent. Instead of using traditional lane markings, the lanes in this dataset are represented by centerlines, which offer a more suitable representation of lanes and their connections. In this study, we have introduced a new approach called TopoMask for predicting centerlines in road topology. Unlike existing approaches in the literature that rely on keypoints or parametric methods, TopoMask utilizes an instance-mask based formulation with a transformer-based architecture and, in order to enrich the mask instances with flow information, a direction label representation is proposed. TopoMask have ranked 4th in the OpenLane-V2 Score (OLS) and ranked 2nd in the F1 score of centerline prediction in OpenLane Topology Challenge 2023. In comparison to the current state-of-the-art method, TopoNet, the proposed method has achieved similar performance in Frechet-based lane detection and outperformed TopoNet in Chamfer-based lane detection without utilizing its scene graph neural network.

cs.CV↗

arXiv2023

SparseSwin: Swin Transformer with Sparse Transformer Block

Advancements in computer vision research have put transformer architecture as the state of the art in computer vision tasks. One of the known drawbacks of the transformer architecture is the high number of parameters, this can lead to a more complex and inefficient algorithm. This paper aims to reduce the number of parameters and in turn, made the transformer more efficient. We present Sparse Transformer (SparTa) Block, a modified transformer block with an addition of a sparse token converter that reduces the number of tokens used. We use the SparTa Block inside the Swin T architecture (SparseSwin) to leverage Swin capability to downsample its input and reduce the number of initial tokens to be calculated. The proposed SparseSwin model outperforms other state of the art models in image classification with an accuracy of 86.96%, 97.43%, and 85.35% on the ImageNet100, CIFAR10, and CIFAR100 datasets respectively. Despite its fewer parameters, the result highlights the potential of a transformer architecture using a sparse token converter with a limited number of tokens to optimize the use of the transformer and improve its performance.

cs.CV↗

arXiv2021

Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces

Most of the existing deep learning based end-to-end image/video coding (DLEC) architectures are designed for non-subsampled RGB color format. However, in order to achieve a superior coding performance, many state-of-the-art block-based compression standards such as High Efficiency Video Coding (HEVC/H.265) and Versatile Video Coding (VVC/H.266) are designed primarily for YUV 4:2:0 format, where U and V components are subsampled by considering the human visual system. This paper investigates various DLEC designs to support YUV 4:2:0 format by comparing their performance against the main profiles of HEVC and VVC standards under a common evaluation framework. Moreover, a new transform network architecture is proposed to improve the efficiency of coding YUV 4:2:0 data. The experimental results on YUV 4:2:0 datasets show that the proposed architecture significantly outperforms naive extensions of existing architectures designed for RGB format and achieves about 10% average BD-rate improvement over the intra-frame coding in HEVC.

eess.IV↗

arXiv2023

Designing Robust Transformers using Robust Kernel Density Estimation

Recent advances in Transformer architectures have empowered their empirical success in a variety of tasks across different domains. However, existing works mainly focus on predictive accuracy and computational cost, without considering other practical issues, such as robustness to contaminated samples. Recent work by Nguyen et al., (2022) has shown that the self-attention mechanism, which is the center of the Transformer architecture, can be viewed as a non-parametric estimator based on kernel density estimation (KDE). This motivates us to leverage a set of robust kernel density estimation methods for alleviating the issue of data contamination. Specifically, we introduce a series of self-attention mechanisms that can be incorporated into different Transformer architectures and discuss the special properties of each method. We then perform extensive empirical studies on language modeling and image classification tasks. Our methods demonstrate robust performance in multiple scenarios while maintaining competitive results on clean datasets.

cs.LG↗

arXiv2024

Self-Satisfied: An end-to-end framework for SAT generation and prediction

The boolean satisfiability (SAT) problem asks whether there exists an assignment of boolean values to the variables of an arbitrary boolean formula making the formula evaluate to True. It is well-known that all NP-problems can be coded as SAT problems and therefore SAT is important both practically and theoretically. From both of these perspectives, better understanding the patterns and structure implicit in SAT data is of significant value. In this paper, we describe several advances that we believe will help open the door to such understanding: we introduce hardware accelerated algorithms for fast SAT problem generation, a geometric SAT encoding that enables the use of transformer architectures typically applied to vision tasks, and a simple yet effective technique we term head slicing for reducing sequence length representation inside transformer architectures. These advances allow us to scale our approach to SAT problems with thousands of variables and tens of thousands of clauses. We validate our architecture, termed Satisfiability Transformer (SaT), on the SAT prediction task with data from the SAT Competition (SATComp) 2022 problem sets. Prior related work either leveraged a pure machine learning approach, but could not handle SATComp-sized problems, or was hybrid in the sense of integrating a machine learning component in a standard SAT solving tool. Our pure machine learning approach achieves prediction accuracies comparable to recent work, but on problems that are an order of magnitude larger than previously demonstrated. A fundamental aspect of our work concerns the very nature of SAT data and its suitability for training machine learning models. We both describe experimental results that probe the landscape of where SAT data can be successfully used for learning and position these results within the broader context of complexity and learning.

cs.LG↗