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 1,495 records · Page 83Linked to original sources

arXiv2022

RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild

Recent advances in self-supervised learning (SSL) using large models to learn visual representations from natural images are rapidly closing the gap between the results produced by fully supervised learning and those produced by SSL on downstream vision tasks. Inspired by this advancement and primarily motivated by the emergence of tabular and structured document image applications, we investigate which self-supervised pretraining objectives, architectures, and fine-tuning strategies are most effective. To address these questions, we introduce RegCLR, a new self-supervised framework that combines contrastive and regularized methods and is compatible with the standard Vision Transformer architecture. Then, RegCLR is instantiated by integrating masked autoencoders as a representative example of a contrastive method and enhanced Barlow Twins as a representative example of a regularized method with configurable input image augmentations in both branches. Several real-world table recognition scenarios (e.g., extracting tables from document images), ranging from standard Word and Latex documents to even more challenging electronic health records (EHR) computer screen images, have been shown to benefit greatly from the representations learned from this new framework, with detection average-precision (AP) improving relatively by 4.8% for Table, 11.8% for Column, and 11.1% for GUI objects over a previous fully supervised baseline on real-world EHR screen images.

cs.CV↗

arXiv2023

Attention Is Not All You Need Anymore

In recent years, the popular Transformer architecture has achieved great success in many application areas, including natural language processing and computer vision. Many existing works aim to reduce the computational and memory complexity of the self-attention mechanism in the Transformer by trading off performance. However, performance is key for the continuing success of the Transformer. In this paper, a family of drop-in replacements for the self-attention mechanism in the Transformer, called the Extractors, is proposed. Four types of the Extractors, namely the super high-performance Extractor (SHE), the higher-performance Extractor (HE), the worthwhile Extractor (WE), and the minimalist Extractor (ME), are proposed as examples. Experimental results show that replacing the self-attention mechanism with the SHE evidently improves the performance of the Transformer, whereas the simplified versions of the SHE, i.e., the HE, the WE, and the ME, perform close to or better than the self-attention mechanism with less computational and memory complexity. Furthermore, the proposed Extractors have the potential or are able to run faster than the self-attention mechanism since their critical paths of computation are much shorter. Additionally, the sequence prediction problem in the context of text generation is formulated using variable-length discrete-time Markov chains, and the Transformer is reviewed based on our understanding.

cs.LG↗

arXiv2023

Sequence Length Independent Norm-Based Generalization Bounds for Transformers

This paper provides norm-based generalization bounds for the Transformer architecture that do not depend on the input sequence length. We employ a covering number based approach to prove our bounds. We use three novel covering number bounds for the function class of bounded linear transformations to upper bound the Rademacher complexity of the Transformer. Furthermore, we show this generalization bound applies to the common Transformer training technique of masking and then predicting the masked word. We also run a simulated study on a sparse majority data set that empirically validates our theoretical findings.

stat.ML↗

arXiv2025

SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC

With the growing use of Transformer models hosted on cloud platforms to offer inference services, privacy concerns are escalating, especially concerning sensitive data like investment plans and bank account details. Secure Multi-Party Computing (SMPC) emerges as a promising solution to protect the privacy of inference data and model parameters. However, the application of SMPC in Privacy-Preserving Inference (PPI) for Transformer models often leads to considerable slowdowns or declines in performance. This is largely due to the multitude of nonlinear operations in the Transformer architecture, which are not well-suited to SMPC and difficult to circumvent or optimize effectively. To address this concern, we introduce a comprehensive PPI framework called SecFormer to achieve fast and accurate PPI for Transformer models. We successfully eliminate the high-cost exponential and maximum operations in PPI without sacrificing model performance and develop a suite of efficient SMPC protocols by employing suitable numerical computation methods to boost other complex nonlinear functions in PPI, including GeLU, LayerNorm, and a redesigned Softmax. Our extensive experiments reveal that SecFormer outperforms MPCFormer in performance, showing improvements of $3.4\%$ and $24.7\%$ for BERT$_{\text{BASE}}$ and BERT$_{\text{LARGE}}$, respectively. In terms of efficiency, SecFormer is 3.57 and 3.58 times faster than PUMA for BERT$_{\text{BASE}}$ and BERT$_{\text{LARGE}}$, demonstrating its effectiveness and speed.

cs.LG↗

arXiv2024

MGI: Multimodal Contrastive pre-training of Genomic and Medical Imaging

Medicine is inherently a multimodal discipline. Medical images can reflect the pathological changes of cancer and tumors, while the expression of specific genes can influence their morphological characteristics. However, most deep learning models employed for these medical tasks are unimodal, making predictions using either image data or genomic data exclusively. In this paper, we propose a multimodal pre-training framework that jointly incorporates genomics and medical images for downstream tasks. To address the issues of high computational complexity and difficulty in capturing long-range dependencies in genes sequence modeling with MLP or Transformer architectures, we utilize Mamba to model these long genomic sequences. We aligns medical images and genes using a self-supervised contrastive learning approach which combines the Mamba as a genetic encoder and the Vision Transformer (ViT) as a medical image encoder. We pre-trained on the TCGA dataset using paired gene expression data and imaging data, and fine-tuned it for downstream tumor segmentation tasks. The results show that our model outperformed a wide range of related methods.

cs.CV↗

arXiv2024

Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality

Flow control is key to maximize energy efficiency in a wide range of applications. However, traditional flow-control methods face significant challenges in addressing non-linear systems and high-dimensional data, limiting their application in realistic energy systems. This study advances deep-reinforcement-learning (DRL) methods for flow control, particularly focusing on integrating group-invariant networks and positional encoding into DRL architectures. Our methods leverage multi-agent reinforcement learning (MARL) to exploit policy invariance in space, in combination with group-invariant networks to ensure local symmetry invariance. Additionally, a positional encoding inspired by the transformer architecture is incorporated to provide location information to the agents, mitigating action constraints from strict invariance. The proposed methods are verified using a case study of Rayleigh-Bénard convection, where the goal is to minimize the Nusselt number Nu. The group-invariant neural networks (GI-NNs) show faster convergence compared to the base MARL, achieving better average policy performance. The GI-NNs not only cut DRL training time in half but also notably enhance learning reproducibility. Positional encoding further enhances these results, effectively reducing the minimum Nu and stabilizing convergence. Interestingly, group invariant networks specialize in improving learning speed and positional encoding specializes in improving learning quality. These results demonstrate that choosing a suitable feature-representation method according to the purpose as well as the characteristics of each control problem is essential. We believe that the results of this study will not only inspire novel DRL methods with invariant and unique representations, but also provide useful insights for industrial applications.

cs.LG↗

arXiv2024

SPiKE: 3D Human Pose from Point Cloud Sequences

3D Human Pose Estimation (HPE) is the task of locating keypoints of the human body in 3D space from 2D or 3D representations such as RGB images, depth maps or point clouds. Current HPE methods from depth and point clouds predominantly rely on single-frame estimation and do not exploit temporal information from sequences. This paper presents SPiKE, a novel approach to 3D HPE using point cloud sequences. Unlike existing methods that process frames of a sequence independently, SPiKE leverages temporal context by adopting a Transformer architecture to encode spatio-temporal relationships between points across the sequence. By partitioning the point cloud into local volumes and using spatial feature extraction via point spatial convolution, SPiKE ensures efficient processing by the Transformer while preserving spatial integrity per timestamp. Experiments on the ITOP benchmark for 3D HPE show that SPiKE reaches 89.19% mAP, achieving state-of-the-art performance with significantly lower inference times. Extensive ablations further validate the effectiveness of sequence exploitation and our algorithmic choices. Code and models are available at: https://github.com/iballester/SPiKE

cs.CV↗

arXiv2025

Encryption-Friendly LLM Architecture

Large language models (LLMs) offer personalized responses based on user interactions, but this use case raises serious privacy concerns. Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic computations in encrypted states and provides a potential solution for privacy-preserving machine learning (PPML). However, the computational intensity of transformers poses challenges for applying HE to LLMs. In this work, we propose a modified HE-friendly transformer architecture with an emphasis on inference following personalized (private) fine-tuning. Utilizing LoRA fine-tuning and Gaussian kernels, we achieve significant computational speedups -- 6.94x for fine-tuning and 2.3x for inference -- while maintaining performance comparable to plaintext models. Our findings provide a viable proof of concept for offering privacy-preserving LLM services in areas where data protection is crucial. Our code is available on GitHub.

cs.CR↗

arXiv2024

Efficient and Aesthetic UI Design with a Deep Learning-Based Interface Generation Tree Algorithm

This paper presents a novel method for user interface (UI) generation based on the Transformer architecture, addressing the increasing demand for efficient and aesthetically pleasing UI designs in software development. Traditional UI design relies heavily on designers' expertise, which can be time-consuming and costly. Leveraging the capabilities of Transformers, particularly their ability to capture complex design patterns and long-range dependencies, we propose a Transformer-based interface generation tree algorithm. This method constructs a hierarchical representation of UI components as nodes in a tree structure, utilizing pre-trained Transformer models for encoding and decoding. We define a markup language to describe UI components and their properties and use a rich dataset of real-world web and mobile application interfaces for training. The experimental results demonstrate that our approach not only significantly enhances design quality and efficiency but also outperforms traditional models in user satisfaction and aesthetic appeal. We also provide a comparative analysis with existing models, illustrating the advantages of our method in terms of accuracy, user ratings, and design similarity. Overall, our study underscores the potential of the Transformer based approach to revolutionize the UI design process, making it accessible for non-professionals while maintaining high standards of quality.

cs.HC↗

arXiv2025

Deep Semantic Graph Learning via LLM based Node Enhancement

Graph learning has attracted significant attention due to its widespread real-world applications. Current mainstream approaches rely on text node features and obtain initial node embeddings through shallow embedding learning using GNNs, which shows limitations in capturing deep textual semantics. Recent advances in Large Language Models (LLMs) have demonstrated superior capabilities in understanding text semantics, transforming traditional text feature processing. This paper proposes a novel framework that combines Graph Transformer architecture with LLM-enhanced node features. Specifically, we leverage LLMs to generate rich semantic representations of text nodes, which are then processed by a multi-head self-attention mechanism in the Graph Transformer to capture both local and global graph structural information. Our model utilizes the Transformer's attention mechanism to dynamically aggregate neighborhood information while preserving the semantic richness provided by LLM embeddings. Experimental results demonstrate that the LLM-enhanced node features significantly improve the performance of graph learning models on node classification tasks. This approach shows promising results across multiple graph learning tasks, offering a practical direction for combining graph networks with language models.

cs.AI↗

arXiv2025

CF-DETR: Coarse-to-Fine Transformer for Real-Time Object Detection

Detection Transformers (DETR) are increasingly adopted in autonomous vehicle (AV) perception systems due to their superior accuracy over convolutional networks. However, concurrently executing multiple DETR tasks presents significant challenges in meeting firm real-time deadlines (R1) and high accuracy requirements (R2), particularly for safety-critical objects, while navigating the inherent latency-accuracy trade-off under resource constraints. Existing real-time DNN scheduling approaches often treat models generically, failing to leverage Transformer-specific properties for efficient resource allocation. To address these challenges, we propose CF-DETR, an integrated system featuring a novel coarse-to-fine Transformer architecture and a dedicated real-time scheduling framework NPFP**. CF-DETR employs three key strategies (A1: coarse-to-fine inference, A2: selective fine inference, A3: multi-level batch inference) that exploit Transformer properties to dynamically adjust patch granularity and attention scope based on object criticality, aiming to satisfy R2. The NPFP** scheduling framework (A4) orchestrates these adaptive mechanisms A1-A3. It partitions each DETR task into a safety-critical coarse subtask for guaranteed critical object detection within its deadline (ensuring R1), and an optional fine subtask for enhanced overall accuracy (R2), while managing individual and batched execution. Our extensive evaluations on server, GPU-enabled embedded platforms, and actual AV platforms demonstrate that CF-DETR, under an NPFP** policy, successfully meets strict timing guarantees for critical operations and achieves significantly higher overall and critical object detection accuracy compared to existing baselines across diverse AV workloads.

eess.SY↗

arXiv2025

MENDR: Manifold Explainable Neural Data Representations

Foundation models for electroencephalography (EEG) signals have recently demonstrated success in learning generalized representations of EEGs, outperforming specialized models in various downstream tasks. However, many of these models lack transparency in their pretraining dynamics and offer limited insight into how well EEG information is preserved within their embeddings. For successful clinical integration, EEG foundation models must ensure transparency in pretraining, downstream fine-tuning, and the interpretability of learned representations. Current approaches primarily operate in the temporal domain, overlooking advancements in digital signal processing that enable the extraction of deterministic and traceable features, such as wavelet-based representations. We propose MENDR (Manifold Explainable Neural Data Representations), a filter bank-based EEG foundation model built on a novel Riemannian Manifold Transformer architecture to resolve these issues. MENDR learns symmetric positive definite matrix embeddings of EEG signals and is pretrained on a large corpus comprising over 4,000 hours of EEG data, decomposed via discrete wavelet packet transforms into multi-resolution coefficients. MENDR significantly enhances interpretability by visualizing symmetric positive definite embeddings as geometric ellipsoids and supports accurate reconstruction of EEG signals from learned embeddings. Evaluations across multiple clinical EEG tasks demonstrate that MENDR achieves near state-of-the-art performance with substantially fewer parameters, underscoring its potential for efficient, interpretable, and clinically applicable EEG analysis.

cs.LG↗

arXiv2025

UniSTFormer: Unified Spatio-Temporal Lightweight Transformer for Efficient Skeleton-Based Action Recognition

Skeleton-based action recognition (SAR) has achieved impressive progress with transformer architectures. However, existing methods often rely on complex module compositions and heavy designs, leading to increased parameter counts, high computational costs, and limited scalability. In this paper, we propose a unified spatio-temporal lightweight transformer framework that integrates spatial and temporal modeling within a single attention module, eliminating the need for separate temporal modeling blocks. This approach reduces redundant computations while preserving temporal awareness within the spatial modeling process. Furthermore, we introduce a simplified multi-scale pooling fusion module that combines local and global pooling pathways to enhance the model's ability to capture fine-grained local movements and overarching global motion patterns. Extensive experiments on benchmark datasets demonstrate that our lightweight model achieves a superior balance between accuracy and efficiency, reducing parameter complexity by over 58% and lowering computational cost by over 60% compared to state-of-the-art transformer-based baselines, while maintaining competitive recognition performance.

cs.CV↗

arXiv2026

Routing without Forgetting

Continual learning in transformers is commonly addressed through parameter-efficient adaptation: prompts, adapters, or LoRA modules are specialized per task while the backbone remains frozen. Although effective in controlled multi-epoch settings, these approaches rely on gradual gradient-based specialization and struggle in Online Continual Learning (OCL), where data arrive as a non-stationary stream and each sample may be observed only once. We recast continual learning in transformers as a routing problem: under strict online constraints, the model must dynamically select the appropriate representational subspace for each input without explicit task identifiers or repeated optimization. We thus introduce Routing without Forgetting (RwF), a transformer architecture augmented with energy-based associative retrieval layers inspired by Modern Hopfield Networks. Instead of storing or merging task-specific prompts, RwF generates dynamic prompts through single-step associative retrieval over the transformer token embeddings at each layer. Retrieval corresponds to the closed-form minimization of a strictly convex free-energy functional, enabling input-conditioned routing within each forward pass, independently of iterative gradient refinement. Across challenging class-incremental benchmarks, RwF improves over existing prompt-based methods. On Split-ImageNet-R and Split-ImageNet-S, RwF outperforms prior prompt-based approaches by a large margin, even in few-shot learning regimes. These results indicate that embedding energy-based associative routing directly within the transformer backbone provides a principled and effective foundation for OCL.

cs.LG↗

arXiv2026

Transformers for Program Termination

Determining whether a program terminates is a core challenge in program analysis with direct implications for correctness, verification, and security. We investigate whether transformer architectures can recognise termination patterns directly from source code and how their strengths can be amplified through ensembles. To overcome the extreme scarcity of non-terminating examples, we design an ensemble framework of compact transformer encoders, systematically trained with a suite of imbalance-aware loss functions and class-aware sampling techniques. By combining models trained with distinct loss functions, our ensembles achieve substantially stronger performance than any single transformer, outperforming both powerful off-the-shelf LLMs and graph-based methods. Finally, we introduce an attribution pipeline that produces syntax-aware explanations for the termination estimation.

cs.PL↗

arXiv2026

OCH3R: Object-Centric Holistic 3D Reconstruction

Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D reconstruction. Such methods are computationally expensive, fragile to segmentation errors, and scale poorly with scene complexity. We introduce OCH3R, a unified framework for Object-Centric Holistic 3D Reconstruction from a single RGB image. OCH3R performs one forward pass to simultaneously predict all object instances with their 6D poses and detailed 3D reconstructions. The key idea is a transformer architecture that predicts per-pixel attributes, including CLIP-based category embeddings, metric depth, normalized object coordinates (NOCS), and a fixed number of 3D Gaussians representing each object. To supervise these Gaussian reconstructions, we transform them into canonical space using the predicted 6D poses and align them with pre-rendered canonical ground truth, avoiding costly per-image Gaussian label generation. On standard indoor benchmarks, OCH3R achieves state-of-the-art performance across monocular depth estimation, open-vocabulary semantic segmentation, and RGB-only category-level 6D pose estimation, while producing high-fidelity, editable per-object reconstructions. Crucially, inference is fully feed-forward and scales independently of the number of objects, offering orders-of-magnitude speedups over conventional multi-stage pipelines in cluttered scenes.

cs.CV↗

arXiv2025

AI-Driven Radiology Report Generation for Traumatic Brain Injuries

Traumatic brain injuries present significant diagnostic challenges in emergency medicine, where the timely interpretation of medical images is crucial for patient outcomes. In this paper, we propose a novel AI-based approach for automatic radiology report generation tailored to cranial trauma cases. Our model integrates an AC-BiFPN with a Transformer architecture to capture and process complex medical imaging data such as CT and MRI scans. The AC-BiFPN extracts multi-scale features, enabling the detection of intricate anomalies like intracranial hemorrhages, while the Transformer generates coherent, contextually relevant diagnostic reports by modeling long-range dependencies. We evaluate the performance of our model on the RSNA Intracranial Hemorrhage Detection dataset, where it outperforms traditional CNN-based models in both diagnostic accuracy and report generation. This solution not only supports radiologists in high-pressure environments but also provides a powerful educational tool for trainee physicians, offering real-time feedback and enhancing their learning experience. Our findings demonstrate the potential of combining advanced feature extraction with transformer-based text generation to improve clinical decision-making in the diagnosis of traumatic brain injuries.

eess.IV↗

arXiv2024

Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images

Recent advancements in autoregressive networks with linear complexity have driven significant research progress, demonstrating exceptional performance in large language models. A representative model is the Extended Long Short-Term Memory (xLSTM), which incorporates gating mechanisms and memory structures, performing comparably to Transformer architectures in long-sequence language tasks. Autoregressive networks such as xLSTM can utilize image serialization to extend their application to visual tasks such as classification and segmentation. Although existing studies have demonstrated Vision-LSTM's impressive results in image classification, its performance in image semantic segmentation remains unverified. Our study represents the first attempt to evaluate the effectiveness of Vision-LSTM in the semantic segmentation of remotely sensed images. This evaluation is based on a specifically designed encoder-decoder architecture named Seg-LSTM, and comparisons with state-of-the-art segmentation networks. Our study found that Vision-LSTM's performance in semantic segmentation was limited and generally inferior to Vision-Transformers-based and Vision-Mamba-based models in most comparative tests. Future research directions for enhancing Vision-LSTM are recommended. The source code is available from https://github.com/zhuqinfeng1999/Seg-LSTM.

cs.CV↗