SEARCH · Search arXiv

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 757 records · Page 42Linked to original sources

arXiv2026

Transformer Circuits Can Realize Clustering Algorithms

Although transformers are most commonly optimized as statistical sequence models, it is unclear to what extent they can implement and learn exact algorithmic computations. Here, we specify a transformer implementation from first principles that executes a fundamental and widely used method for $k$-means clustering: Lloyd's algorithm. We theoretically prove and empirically demonstrate that this implementation of a transformer architecture, which we term the $k$-means transformer, exactly implements Lloyd's algorithm for $k$-means clustering using the standard circuit mechanisms of modern transformers: attention block, residual connections, and feed-forward block. In learning experiments, we find that training this base architecture on $k$-means clustering yields a generalizable clustering algorithm that surpasses Lloyd's algorithm in terms of clustering quality. Finally, we demonstrate that interpretable alterations (e.g., inclusion of layer normalizations) to this architecture yields diverse and novel variants of clustering algorithms, including soft $k$-means, spherical $k$-means, trimmed $k$-means. Overall, our results show that transformer circuit mechanisms can instantiate exact algorithmic routines for clustering, while simultaneously providing an effective learnable model.

cs.LG↗

arXiv2024

Self-Supervised Pre-Training for Table Structure Recognition Transformer

Table structure recognition (TSR) aims to convert tabular images into a machine-readable format. Although hybrid convolutional neural network (CNN)-transformer architecture is widely used in existing approaches, linear projection transformer has outperformed the hybrid architecture in numerous vision tasks due to its simplicity and efficiency. However, existing research has demonstrated that a direct replacement of CNN backbone with linear projection leads to a marked performance drop. In this work, we resolve the issue by proposing a self-supervised pre-training (SSP) method for TSR transformers. We discover that the performance gap between the linear projection transformer and the hybrid CNN-transformer can be mitigated by SSP of the visual encoder in the TSR model. We conducted reproducible ablation studies and open-sourced our code at https://github.com/poloclub/unitable to enhance transparency, inspire innovations, and facilitate fair comparisons in our domain as tables are a promising modality for representation learning.

cs.CV↗

arXiv2022

Geometric Transformer for End-to-End Molecule Properties Prediction

Transformers have become methods of choice in many applications thanks to their ability to represent complex interactions between elements. However, extending the Transformer architecture to non-sequential data such as molecules and enabling its training on small datasets remains a challenge. In this work, we introduce a Transformer-based architecture for molecule property prediction, which is able to capture the geometry of the molecule. We modify the classical positional encoder by an initial encoding of the molecule geometry, as well as a learned gated self-attention mechanism. We further suggest an augmentation scheme for molecular data capable of avoiding the overfitting induced by the overparameterized architecture. The proposed framework outperforms the state-of-the-art methods while being based on pure machine learning solely, i.e. the method does not incorporate domain knowledge from quantum chemistry and does not use extended geometric inputs besides the pairwise atomic distances.

cs.LG↗

arXiv2024

DeMansia: Mamba Never Forgets Any Tokens

This paper examines the mathematical foundations of transformer architectures, highlighting their limitations particularly in handling long sequences. We explore prerequisite models such as Mamba, Vision Mamba (ViM), and LV-ViT that pave the way for our proposed architecture, DeMansia. DeMansia integrates state space models with token labeling techniques to enhance performance in image classification tasks, efficiently addressing the computational challenges posed by traditional transformers. The architecture, benchmark, and comparisons with contemporary models demonstrate DeMansia's effectiveness. The implementation of this paper is available on GitHub at https://github.com/catalpaaa/DeMansia

cs.CV↗

arXiv2023

Transformer variational wave functions for frustrated quantum spin systems

The Transformer architecture has become the state-of-art model for natural language processing tasks and, more recently, also for computer vision tasks, thus defining the Vision Transformer (ViT) architecture. The key feature is the ability to describe long-range correlations among the elements of the input sequences, through the so-called self-attention mechanism. Here, we propose an adaptation of the ViT architecture with complex parameters to define a new class of variational neural-network states for quantum many-body systems, the ViT wave function. We apply this idea to the one-dimensional $J_1$-$J_2$ Heisenberg model, demonstrating that a relatively simple parametrization gets excellent results for both gapped and gapless phases. In this case, excellent accuracies are obtained by a relatively shallow architecture, with a single layer of self-attention, thus largely simplifying the original architecture. Still, the optimization of a deeper structure is possible and can be used for more challenging models, most notably highly-frustrated systems in two dimensions. The success of the ViT wave function relies on mixing both local and global operations, thus enabling the study of large systems with high accuracy.

cond-mat.dis-nn↗

arXiv2024

Enhancing Neural Machine Translation of Low-Resource Languages: Corpus Development, Human Evaluation and Explainable AI Architectures

In the current machine translation (MT) landscape, the Transformer architecture stands out as the gold standard, especially for high-resource language pairs. This research delves into its efficacy for low-resource language pairs including both the English$\leftrightarrow$Irish and English$\leftrightarrow$Marathi language pairs. Notably, the study identifies the optimal hyperparameters and subword model type to significantly improve the translation quality of Transformer models for low-resource language pairs. The scarcity of parallel datasets for low-resource languages can hinder MT development. To address this, gaHealth was developed, the first bilingual corpus of health data for the Irish language. Focusing on the health domain, models developed using this in-domain dataset exhibited very significant improvements in BLEU score when compared with models from the LoResMT2021 Shared Task. A subsequent human evaluation using the multidimensional quality metrics error taxonomy showcased the superior performance of the Transformer system in reducing both accuracy and fluency errors compared to an RNN-based counterpart. Furthermore, this thesis introduces adaptNMT and adaptMLLM, two open-source applications streamlined for the development, fine-tuning, and deployment of neural machine translation models. These tools considerably simplify the setup and evaluation process, making MT more accessible to both developers and translators. Notably, adaptNMT, grounded in the OpenNMT ecosystem, promotes eco-friendly natural language processing research by highlighting the environmental footprint of model development. Fine-tuning of MLLMs by adaptMLLM demonstrated advancements in translation performance for two low-resource language pairs: English$\leftrightarrow$Irish and English$\leftrightarrow$Marathi, compared to baselines from the LoResMT2021 Shared Task.

cs.CL↗

arXiv2021

Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks

Sign languages are multi-channel visual languages, where signers use a continuous 3D space to communicate.Sign Language Production (SLP), the automatic translation from spoken to sign languages, must embody both the continuous articulation and full morphology of sign to be truly understandable by the Deaf community. Previous deep learning-based SLP works have produced only a concatenation of isolated signs focusing primarily on the manual features, leading to a robotic and non-expressive production. In this work, we propose a novel Progressive Transformer architecture, the first SLP model to translate from spoken language sentences to continuous 3D multi-channel sign pose sequences in an end-to-end manner. Our transformer network architecture introduces a counter decoding that enables variable length continuous sequence generation by tracking the production progress over time and predicting the end of sequence. We present extensive data augmentation techniques to reduce prediction drift, alongside an adversarial training regime and a Mixture Density Network (MDN) formulation to produce realistic and expressive sign pose sequences. We propose a back translation evaluation mechanism for SLP, presenting benchmark quantitative results on the challenging PHOENIX14T dataset and setting baselines for future research. We further provide a user evaluation of our SLP model, to understand the Deaf reception of our sign pose productions.

cs.CV↗

arXiv2021

Higher Order Recurrent Space-Time Transformer for Video Action Prediction

Endowing visual agents with predictive capability is a key step towards video intelligence at scale. The predominant modeling paradigm for this is sequence learning, mostly implemented through LSTMs. Feed-forward Transformer architectures have replaced recurrent model designs in ML applications of language processing and also partly in computer vision. In this paper we investigate on the competitiveness of Transformer-style architectures for video predictive tasks. To do so we propose HORST, a novel higher order recurrent layer design whose core element is a spatial-temporal decomposition of self-attention for video. HORST achieves state of the art competitive performance on Something-Something early action recognition and EPIC-Kitchens action anticipation, showing evidence of predictive capability that we attribute to our recurrent higher order design of self-attention.

cs.CV↗

arXiv2020

Image Captioning through Image Transformer

Automatic captioning of images is a task that combines the challenges of image analysis and text generation. One important aspect in captioning is the notion of attention: How to decide what to describe and in which order. Inspired by the successes in text analysis and translation, previous work have proposed the \textit{transformer} architecture for image captioning. However, the structure between the \textit{semantic units} in images (usually the detected regions from object detection model) and sentences (each single word) is different. Limited work has been done to adapt the transformer's internal architecture to images. In this work, we introduce the \textbf{\textit{image transformer}}, which consists of a modified encoding transformer and an implicit decoding transformer, motivated by the relative spatial relationship between image regions. Our design widen the original transformer layer's inner architecture to adapt to the structure of images. With only regions feature as inputs, our model achieves new state-of-the-art performance on both MSCOCO offline and online testing benchmarks.

cs.CV↗

arXiv2025

Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition

Human Activity Recognition (HAR) on mobile devices has been demonstrated to be possible using neural models trained on data collected from the device's inertial measurement units. These models have used Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), Transformers or a combination of these to achieve state-of-the-art results with real-time performance. However, these approaches have not been extensively evaluated in real-world situations where the input data may be different from the training data. This paper highlights the issue of data heterogeneity in machine learning applications and how it can hinder their deployment in pervasive settings. To address this problem, we propose and publicly release the code of two sensor-wise Transformer architectures called HART and MobileHART for Human Activity Recognition Transformer. Our experiments on several publicly available datasets show that these HART architectures outperform previous architectures with fewer floating point operations and parameters than conventional Transformers. The results also show they are more robust to changes in mobile position or device brand and hence better suited for the heterogeneous environments encountered in real-life settings. Finally, the source code has been made publicly available.

cs.CV↗

arXiv2025

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using only gradient-based learning on next-token prediction. While the core component of a transformer is the self-attention mechanism, we question how much, and which aspects, of the performance gains can be attributed to it. To this end, we compare standard transformers to variants in which either the MLP layers or the attention weights are frozen at initialization. Surprisingly, we find that attention with frozen key and query weights is not only able to form induction heads, but can also perform competitively on language modeling. We formalize this by proving a new expressivity result for transformer models with frozen key and query weights. To further isolate the contribution of attention, we design MixiT, an architecture with entirely random attention scores, with provably stable signal propagation that overcomes prior depth-wise scaling challenges in random transformers. We use the successes and failures of MixiT to understand the role each transformer component plays, such as attention being largely responsible for in-context reasoning, and MLPs being responsible for, but collaborates with attention, on knowledge storage. Our results suggest that the transformer architecture has a built-in inductive bias towards forming specialized circuits, as it does even without learnable attention weights.

cs.LG↗

arXiv2020

End-to-End Multi-speaker Speech Recognition with Transformer

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of Transformer models for these tasks by focusing on two aspects. First, we replace the RNN-based encoder-decoder in the speech recognition model with a Transformer architecture. Second, in order to use the Transformer in the masking network of the neural beamformer in the multi-channel case, we modify the self-attention component to be restricted to a segment rather than the whole sequence in order to reduce computation. Besides the model architecture improvements, we also incorporate an external dereverberation preprocessing, the weighted prediction error (WPE), enabling our model to handle reverberated signals. Experiments on the spatialized wsj1-2mix corpus show that the Transformer-based models achieve 40.9% and 25.6% relative WER reduction, down to 12.1% and 6.4% WER, under the anechoic condition in single-channel and multi-channel tasks, respectively, while in the reverberant case, our methods achieve 41.5% and 13.8% relative WER reduction, down to 16.5% and 15.2% WER.

eess.AS↗

arXiv2026

PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting

Despite advances in the Transformer architecture, their effectiveness for long-term time series forecasting (LTSF) remains controversial. In this paper, we investigate the potential of integrating explicit periodicity modeling into the self-attention mechanism to enhance the performance of Transformer-based architectures for LTSF. Specifically, we propose PENGUIN, a simple yet effective periodic-nested group attention mechanism. Our approach introduces a periodic-aware relative attention bias to directly capture periodic structures and a grouped multi-query attention mechanism to handle multiple coexisting periodicities (e.g., daily and weekly cycles) within time series data. Extensive experiments across diverse benchmarks demonstrate that PENGUIN consistently outperforms both MLP-based and Transformer-based models. Code is available at https://github.com/ysygMhdxw/AISTATS2026_PENGUIN.

cs.LG↗

arXiv2022

BayesFormer: Transformer with Uncertainty Estimation

Transformer has become ubiquitous due to its dominant performance in various NLP and image processing tasks. However, it lacks understanding of how to generate mathematically grounded uncertainty estimates for transformer architectures. Models equipped with such uncertainty estimates can typically improve predictive performance, make networks robust, avoid over-fitting and used as acquisition function in active learning. In this paper, we introduce BayesFormer, a Transformer model with dropouts designed by Bayesian theory. We proposed a new theoretical framework to extend the approximate variational inference-based dropout to Transformer-based architectures. Through extensive experiments, we validate the proposed architecture in four paradigms and show improvements across the board: language modeling and classification, long-sequence understanding, machine translation and acquisition function for active learning.

cs.CL↗

arXiv2024

Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data

Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize better to new data and problems. This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios, where sparse experimental data is supplemented with simulation data. The proposed approach integrates transformer-based architecture with a novel graph-based hyper-parameter optimization technique. The resulting system not only effectively reduces simulation bias, but also achieves superior prediction accuracy compared to the prior method. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available, as well as synthetic versions of these experiments.

cs.LG↗

arXiv2025

Compact Vision Transformer by Reduction of Kernel Complexity

Self-attention and transformer architectures have become foundational components in modern deep learning. Recent efforts have integrated transformer blocks into compact neural architectures for computer vision, giving rise to various efficient vision transformers. In this work, we introduce Transformer with Kernel Complexity Reduction, or KCR-Transformer, a compact transformer block equipped with differentiable channel selection, guided by a novel and sharp theoretical generalization bound. KCR-Transformer performs input/output channel selection in the MLP layers of transformer blocks to reduce the computational cost. Furthermore, we provide a rigorous theoretical analysis establishing a tight generalization bound for networks equipped with KCR-Transformer blocks. Leveraging such strong theoretical results, the channel pruning by KCR-Transformer is conducted in a generalization-aware manner, ensuring that the resulting network retains a provably small generalization error. Our KCR-Transformer is compatible with many popular and compact transformer networks, such as ViT and Swin, and it reduces the FLOPs of the vision transformers while maintaining or even improving the prediction accuracy. In the experiments, we replace all the transformer blocks in the vision transformers with KCR-Transformer blocks, leading to KCR-Transformer networks with different backbones. The resulting TCR-Transformers achieve superior performance on various computer vision tasks, achieving even better performance than the original models with even less FLOPs and parameters.

cs.CV↗

arXiv2021

Shape registration in the time of transformers

In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. The proposed approach is data-driven and adopts for the first time the transformer architecture in the registration task. Our method is general and applies to different settings. Given a fixed template with some desired properties (e.g. skinning weights or other animation cues), we can register raw acquired data to it, thereby transferring all the template properties to the input geometry. Alternatively, given a pair of shapes, our method can register the first onto the second (or vice-versa), obtaining a high-quality dense correspondence between the two. In both contexts, the quality of our results enables us to target real applications such as texture transfer and shape interpolation. Furthermore, we also show that including an estimation of the underlying density of the surface eases the learning process. By exploiting the potential of this architecture, we can train our model requiring only a sparse set of ground truth correspondences ($10\sim20\%$ of the total points). The proposed model and the analysis that we perform pave the way for future exploration of transformer-based architectures for registration and matching applications. Qualitative and quantitative evaluations demonstrate that our pipeline outperforms state-of-the-art methods for deformable and unordered 3D data registration on different datasets and scenarios.

cs.CV↗

arXiv2024

UniMuMo: Unified Text, Music and Motion Generation

We introduce UniMuMo, a unified multimodal model capable of taking arbitrary text, music, and motion data as input conditions to generate outputs across all three modalities. To address the lack of time-synchronized data, we align unpaired music and motion data based on rhythmic patterns to leverage existing large-scale music-only and motion-only datasets. By converting music, motion, and text into token-based representation, our model bridges these modalities through a unified encoder-decoder transformer architecture. To support multiple generation tasks within a single framework, we introduce several architectural improvements. We propose encoding motion with a music codebook, mapping motion into the same feature space as music. We introduce a music-motion parallel generation scheme that unifies all music and motion generation tasks into a single transformer decoder architecture with a single training task of music-motion joint generation. Moreover, the model is designed by fine-tuning existing pre-trained single-modality models, significantly reducing computational demands. Extensive experiments demonstrate that UniMuMo achieves competitive results on all unidirectional generation benchmarks across music, motion, and text modalities. Quantitative results are available in the \href{https://hanyangclarence.github.io/unimumo_demo/}{project page}.

cs.SD↗