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 775 records · Page 43Linked to original sources

arXiv2025

A Deep-Unfolding Approach to RIS Phase Shift Optimization Via Transformer-Based Channel Prediction

Reconfigurable intelligent surfaces (RISs) have emerged as a promising solution that can provide dynamic control over the propagation of electromagnetic waves. The RIS technology is envisioned as a key enabler of sixth-generation networks by offering the ability to adaptively manipulate signal propagation through the smart configuration of its phase shift coefficients, thereby optimizing signal strength, coverage, and capacity. However, the realization of this technology's full potential hinges on the accurate acquisition of channel state information (CSI). In this paper, we propose an efficient CSI prediction framework for a RIS-assisted communication system based on the machine learning (ML) transformer architecture. Architectural modifications are introduced to the vanilla transformer for multivariate time series forecasting to achieve high prediction accuracy. The predicted channel coefficients are then used to optimize the RIS phase shifts. Simulation results present a comprehensive analysis of key performance metrics, including data rate and outage probability. Our results confirm the effectiveness of the proposed ML approach and demonstrate its superiority over other baseline ML-based CSI prediction schemes such as conventional deep neural networks and long short-term memory architectures, albeit at the cost of slightly increased complexity.

eess.SP↗

arXiv2026

Efficient Equivariant Transformer for Self-Driving Agent Modeling

Accurately modeling agent behaviors is an important task in self-driving. It is also a task with many symmetries, such as equivariance to the order of agents and objects in the scene or equivariance to arbitrary roto-translations of the entire scene as a whole; i.e., SE(2)-equivariance. The transformer architecture is a ubiquitous tool for modeling these symmetries. While standard self-attention is inherently permutation equivariant, explicit pairwise relative positional encodings have been the standard for introducing SE(2)-equivariance. However, this approach introduces an additional cost that is quadratic in the number of agents, limiting its scalability to larger scenes and batch sizes. In this work, we propose DriveGATr, a novel transformer-based architecture for agent modeling that achieves SE(2)-equivariance without the computational cost of existing methods. Inspired by recent advances in geometric deep learning, DriveGATr encodes scene elements as multivectors in the 2D projective geometric algebra $\mathbb{R}^*_{2,0,1}$ and processes them with a stack of equivariant transformer blocks. Crucially, DriveGATr models geometric relationships using standard attention between multivectors, eliminating the need for costly explicit pairwise relative positional encodings. Experiments on the Waymo Open Motion Dataset demonstrate that DriveGATr is comparable to the state-of-the-art in traffic simulation and establishes a superior Pareto front for performance vs computational cost.

cs.RO↗

arXiv2022

Formal Algorithms for Transformers

This document aims to be a self-contained, mathematically precise overview of transformer architectures and algorithms (*not* results). It covers what transformers are, how they are trained, what they are used for, their key architectural components, and a preview of the most prominent models. The reader is assumed to be familiar with basic ML terminology and simpler neural network architectures such as MLPs.

cs.LG↗

arXiv2018

On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation

This work investigates the alignment problem in state-of-the-art multi-head attention models based on the transformer architecture. We demonstrate that alignment extraction in transformer models can be improved by augmenting an additional alignment head to the multi-head source-to-target attention component. This is used to compute sharper attention weights. We describe how to use the alignment head to achieve competitive performance. To study the effect of adding the alignment head, we simulate a dictionary-guided translation task, where the user wants to guide translation using pre-defined dictionary entries. Using the proposed approach, we achieve up to $3.8$ % BLEU improvement when using the dictionary, in comparison to $2.4$ % BLEU in the baseline case. We also propose alignment pruning to speed up decoding in alignment-based neural machine translation (ANMT), which speeds up translation by a factor of $1.8$ without loss in translation performance. We carry out experiments on the shared WMT 2016 English$\to$Romanian news task and the BOLT Chinese$\to$English discussion forum task.

cs.CL↗

arXiv2022

Explainability of Deep Learning models for Urban Space perception

Deep learning based computer vision models are increasingly used by urban planners to support decision making for shaping urban environments. Such models predict how people perceive the urban environment quality in terms of e.g. its safety or beauty. However, the blackbox nature of deep learning models hampers urban planners to understand what landscape objects contribute to a particularly high quality or low quality urban space perception. This study investigates how computer vision models can be used to extract relevant policy information about peoples' perception of the urban space. To do so, we train two widely used computer vision architectures; a Convolutional Neural Network and a transformer, and apply GradCAM -- a well-known ex-post explainable AI technique -- to highlight the image regions important for the model's prediction. Using these GradCAM visualizations, we manually annotate the objects relevant to the models' perception predictions. As a result, we are able to discover new objects that are not represented in present object detection models used for annotation in previous studies. Moreover, our methodological results suggest that transformer architectures are better suited to be used in combination with GradCAM techniques. Code is available on Github.

cs.CV↗

arXiv2022

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

As a pioneering work exploring transformer architecture for 3D point cloud understanding, Point Transformer achieves impressive results on multiple highly competitive benchmarks. In this work, we analyze the limitations of the Point Transformer and propose our powerful and efficient Point Transformer V2 model with novel designs that overcome the limitations of previous work. In particular, we first propose group vector attention, which is more effective than the previous version of vector attention. Inheriting the advantages of both learnable weight encoding and multi-head attention, we present a highly effective implementation of grouped vector attention with a novel grouped weight encoding layer. We also strengthen the position information for attention by an additional position encoding multiplier. Furthermore, we design novel and lightweight partition-based pooling methods which enable better spatial alignment and more efficient sampling. Extensive experiments show that our model achieves better performance than its predecessor and achieves state-of-the-art on several challenging 3D point cloud understanding benchmarks, including 3D point cloud segmentation on ScanNet v2 and S3DIS and 3D point cloud classification on ModelNet40. Our code will be available at https://github.com/Gofinge/PointTransformerV2.

cs.CV↗

arXiv2022

Spatio-Temporal Hybrid Fusion of CAE and SWIn Transformers for Lung Cancer Malignancy Prediction

The paper proposes a novel hybrid discovery Radiomics framework that simultaneously integrates temporal and spatial features extracted from non-thin chest Computed Tomography (CT) slices to predict Lung Adenocarcinoma (LUAC) malignancy with minimum expert involvement. Lung cancer is the leading cause of mortality from cancer worldwide and has various histologic types, among which LUAC has recently been the most prevalent. LUACs are classified as pre-invasive, minimally invasive, and invasive adenocarcinomas. Timely and accurate knowledge of the lung nodules malignancy leads to a proper treatment plan and reduces the risk of unnecessary or late surgeries. Currently, chest CT scan is the primary imaging modality to assess and predict the invasiveness of LUACs. However, the radiologists' analysis based on CT images is subjective and suffers from a low accuracy compared to the ground truth pathological reviews provided after surgical resections. The proposed hybrid framework, referred to as the CAET-SWin, consists of two parallel paths: (i) The Convolutional Auto-Encoder (CAE) Transformer path that extracts and captures informative features related to inter-slice relations via a modified Transformer architecture, and; (ii) The Shifted Window (SWin) Transformer path, which is a hierarchical vision transformer that extracts nodules' related spatial features from a volumetric CT scan. Extracted temporal (from the CAET-path) and spatial (from the Swin path) are then fused through a fusion path to classify LUACs. Experimental results on our in-house dataset of 114 pathologically proven Sub-Solid Nodules (SSNs) demonstrate that the CAET-SWin significantly improves reliability of the invasiveness prediction task while achieving an accuracy of 82.65%, sensitivity of 83.66%, and specificity of 81.66% using 10-fold cross-validation.

eess.IV↗

arXiv2023

ABC: Attention with Bilinear Correlation for Infrared Small Target Detection

Infrared small target detection (ISTD) has a wide range of applications in early warning, rescue, and guidance. However, CNN based deep learning methods are not effective at segmenting infrared small target (IRST) that it lack of clear contour and texture features, and transformer based methods also struggle to achieve significant results due to the absence of convolution induction bias. To address these issues, we propose a new model called attention with bilinear correlation (ABC), which is based on the transformer architecture and includes a convolution linear fusion transformer (CLFT) module with a novel attention mechanism for feature extraction and fusion, which effectively enhances target features and suppresses noise. Additionally, our model includes a u-shaped convolution-dilated convolution (UCDC) module located deeper layers of the network, which takes advantage of the smaller resolution of deeper features to obtain finer semantic information. Experimental results on public datasets demonstrate that our approach achieves state-of-the-art performance. Code is available at https://github.com/PANPEIWEN/ABC

cs.CV↗

arXiv2024

MUDiff: Unified Diffusion for Complete Molecule Generation

Molecule generation is a very important practical problem, with uses in drug discovery and material design, and AI methods promise to provide useful solutions. However, existing methods for molecule generation focus either on 2D graph structure or on 3D geometric structure, which is not sufficient to represent a complete molecule as 2D graph captures mainly topology while 3D geometry captures mainly spatial atom arrangements. Combining these representations is essential to better represent a molecule. In this paper, we present a new model for generating a comprehensive representation of molecules, including atom features, 2D discrete molecule structures, and 3D continuous molecule coordinates, by combining discrete and continuous diffusion processes. The use of diffusion processes allows for capturing the probabilistic nature of molecular processes and exploring the effect of different factors on molecular structures. Additionally, we propose a novel graph transformer architecture to denoise the diffusion process. The transformer adheres to 3D roto-translation equivariance constraints, allowing it to learn invariant atom and edge representations while preserving the equivariance of atom coordinates. This transformer can be used to learn molecular representations robust to geometric transformations. We evaluate the performance of our model through experiments and comparisons with existing methods, showing its ability to generate more stable and valid molecules. Our model is a promising approach for designing stable and diverse molecules and can be applied to a wide range of tasks in molecular modeling.

cs.LG↗

arXiv2023

Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection

Scene graph generation (SGG) and human-object interaction (HOI) detection are two important visual tasks aiming at localising and recognising relationships between objects, and interactions between humans and objects, respectively. Prevailing works treat these tasks as distinct tasks, leading to the development of task-specific models tailored to individual datasets. However, we posit that the presence of visual relationships can furnish crucial contextual and intricate relational cues that significantly augment the inference of human-object interactions. This motivates us to think if there is a natural intrinsic relationship between the two tasks, where scene graphs can serve as a source for inferring human-object interactions. In light of this, we introduce SG2HOI+, a unified one-step model based on the Transformer architecture. Our approach employs two interactive hierarchical Transformers to seamlessly unify the tasks of SGG and HOI detection. Concretely, we initiate a relation Transformer tasked with generating relation triples from a suite of visual features. Subsequently, we employ another transformer-based decoder to predict human-object interactions based on the generated relation triples. A comprehensive series of experiments conducted across established benchmark datasets including Visual Genome, V-COCO, and HICO-DET demonstrates the compelling performance of our SG2HOI+ model in comparison to prevalent one-stage SGG models. Remarkably, our approach achieves competitive performance when compared to state-of-the-art HOI methods. Additionally, we observe that our SG2HOI+ jointly trained on both SGG and HOI tasks in an end-to-end manner yields substantial improvements for both tasks compared to individualized training paradigms.

cs.CV↗

arXiv2023

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer

The field of 4D point cloud understanding is rapidly developing with the goal of analyzing dynamic 3D point cloud sequences. However, it remains a challenging task due to the sparsity and lack of texture in point clouds. Moreover, the irregularity of point cloud poses a difficulty in aligning temporal information within video sequences. To address these issues, we propose a novel cross-modal knowledge transfer framework, called X4D-SceneFormer. This framework enhances 4D-Scene understanding by transferring texture priors from RGB sequences using a Transformer architecture with temporal relationship mining. Specifically, the framework is designed with a dual-branch architecture, consisting of an 4D point cloud transformer and a Gradient-aware Image Transformer (GIT). During training, we employ multiple knowledge transfer techniques, including temporal consistency losses and masked self-attention, to strengthen the knowledge transfer between modalities. This leads to enhanced performance during inference using single-modal 4D point cloud inputs. Extensive experiments demonstrate the superior performance of our framework on various 4D point cloud video understanding tasks, including action recognition, action segmentation and semantic segmentation. The results achieve 1st places, i.e., 85.3% (+7.9%) accuracy and 47.3% (+5.0%) mIoU for 4D action segmentation and semantic segmentation, on the HOI4D challenge\footnote{\url{http://www.hoi4d.top/}.}, outperforming previous state-of-the-art by a large margin. We release the code at https://github.com/jinglinglingling/X4D

cs.CV↗

arXiv2024

Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data

Large language models (LLMs) are powerful models that can learn concepts at the inference stage via in-context learning (ICL). While theoretical studies, e.g., \cite{zhang2023trained}, attempt to explain the mechanism of ICL, they assume the input $x_i$ and the output $y_i$ of each demonstration example are in the same token (i.e., structured data). However, in real practice, the examples are usually text input, and all words, regardless of their logic relationship, are stored in different tokens (i.e., unstructured data \cite{wibisono2023role}). To understand how LLMs learn from the unstructured data in ICL, this paper studies the role of each component in the transformer architecture and provides a theoretical understanding to explain the success of the architecture. In particular, we consider a simple transformer with one/two attention layers and linear regression tasks for the ICL prediction. We observe that (1) a transformer with two layers of (self-)attentions with a look-ahead attention mask can learn from the prompt in the unstructured data, and (2) positional encoding can match the $x_i$ and $y_i$ tokens to achieve a better ICL performance.

cs.LG↗

arXiv2024

Scalable Visual State Space Model with Fractal Scanning

Foundational models have significantly advanced in natural language processing (NLP) and computer vision (CV), with the Transformer architecture becoming a standard backbone. However, the Transformer's quadratic complexity poses challenges for handling longer sequences and higher resolution images. To address this challenge, State Space Models (SSMs) like Mamba have emerged as efficient alternatives, initially matching Transformer performance in NLP tasks and later surpassing Vision Transformers (ViTs) in various CV tasks. To improve the performance of SSMs, one crucial aspect is effective serialization of image patches. Existing methods, relying on linear scanning curves, often fail to capture complex spatial relationships and produce repetitive patterns, leading to biases. To address these limitations, we propose using fractal scanning curves for patch serialization. Fractal curves maintain high spatial proximity and adapt to different image resolutions, avoiding redundancy and enhancing SSMs' ability to model complex patterns accurately. We validate our method in image classification, detection, and segmentation tasks, and the superior performance validates its effectiveness.

cs.CV↗

arXiv2024

ESCAPE: Equivariant Shape Completion via Anchor Point Encoding

Shape completion, a crucial task in 3D computer vision, involves predicting and filling the missing regions of scanned or partially observed objects. Current methods expect known pose or canonical coordinates and do not perform well under varying rotations, limiting their real-world applicability. We introduce ESCAPE (Equivariant Shape Completion via Anchor Point Encoding), a novel framework designed to achieve rotation-equivariant shape completion. Our approach employs a distinctive encoding strategy by selecting anchor points from a shape and representing all points as a distance to all anchor points. This enables the model to capture a consistent, rotation-equivariant understanding of the object's geometry. ESCAPE leverages a transformer architecture to encode and decode the distance transformations, ensuring that generated shape completions remain accurate and equivariant under rotational transformations. Subsequently, we perform optimization to calculate the predicted shapes from the encodings. Experimental evaluations demonstrate that ESCAPE achieves robust, high-quality reconstructions across arbitrary rotations and translations, showcasing its effectiveness in real-world applications without additional pose estimation modules.

cs.CV↗

arXiv2025

Query Nearby: Offset-Adjusted Mask2Former enhances small-organ segmentation

Medical segmentation plays an important role in clinical applications like radiation therapy and surgical guidance, but acquiring clinically acceptable results is difficult. In recent years, progress has been witnessed with the success of utilizing transformer-like models, such as combining the attention mechanism with CNN. In particular, transformer-based segmentation models can extract global information more effectively, compensating for the drawbacks of CNN modules that focus on local features. However, utilizing transformer architecture is not easy, because training transformer-based models can be resource-demanding. Moreover, due to the distinct characteristics in the medical field, especially when encountering mid-sized and small organs with compact regions, their results often seem unsatisfactory. For example, using ViT to segment medical images directly only gives a DSC of less than 50\%, which is far lower than the clinically acceptable score of 80\%. In this paper, we used Mask2Former with deformable attention to reduce computation and proposed offset adjustment strategies to encourage sampling points within the same organs during attention weights computation, thereby integrating compact foreground information better. Additionally, we utilized the 4th feature map in Mask2Former to provide a coarse location of organs, and employed an FCN-based auxiliary head to help train Mask2Former more quickly using Dice loss. We show that our model achieves SOTA (State-of-the-Art) performance on the HaNSeg and SegRap2023 datasets, especially on mid-sized and small organs.Our code is available at link https://github.com/earis/Offsetadjustment\_Background-location\_Decoder\_Mask2former.

cs.CV↗

arXiv2025

StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing

The visual dubbing task aims to generate mouth movements synchronized with the driving audio, which has seen significant progress in recent years. However, two critical deficiencies hinder their wide application: (1) Audio-only driving paradigms inadequately capture speaker-specific lip habits, which fail to generate lip movements similar to the target avatar; (2) Conventional blind-inpainting approaches frequently produce visual artifacts when handling obstructions (e.g., microphones, hands), limiting practical deployment. In this paper, we propose StableDub, a novel and concise framework integrating lip-habit-aware modeling with occlusion-robust synthesis. Specifically, building upon the Stable-Diffusion backbone, we develop a lip-habit-modulated mechanism that jointly models phonemic audio-visual synchronization and speaker-specific orofacial dynamics. To achieve plausible lip geometries and object appearances under occlusion, we introduce the occlusion-aware training strategy by explicitly exposing the occlusion objects to the inpainting process. By incorporating the proposed designs, the model eliminates the necessity for cost-intensive priors in previous methods, thereby exhibiting superior training efficiency on the computationally intensive diffusion-based backbone. To further optimize training efficiency from the perspective of model architecture, we introduce a hybrid Mamba-Transformer architecture, which demonstrates the enhanced applicability in low-resource research scenarios. Extensive experimental results demonstrate that StableDub achieves superior performance in lip habit resemblance and occlusion robustness. Our method also surpasses other methods in audio-lip sync, video quality, and resolution consistency. We expand the applicability of visual dubbing methods from comprehensive aspects, and demo videos can be found at https://stabledub.github.io.

cs.CV↗

arXiv2025

IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method

High-order numerical methods enhance Transformer performance in tasks like NLP and CV, but introduce a performance-efficiency trade-off due to increased computational overhead. Our analysis reveals that conventional efficiency techniques, such as distillation, can be detrimental to the performance of these models, exemplified by PCformer. To explore more optimizable ODE-based Transformer architectures, we propose the Iterative Implicit Euler Transformer (IIET), which simplifies high-order methods using an iterative implicit Euler approach. This simplification not only leads to superior performance but also facilitates model compression compared to PCformer. To enhance inference efficiency, we introduce Iteration Influence-Aware Distillation (IIAD). Through a flexible threshold, IIAD allows users to effectively balance the performance-efficiency trade-off. On lm-evaluation-harness, IIET boosts average accuracy by 2.65% over vanilla Transformers and 0.8% over PCformer. Its efficient variant, E-IIET, significantly cuts inference overhead by 55% while retaining 99.4% of the original task accuracy. Moreover, the most efficient IIET variant achieves an average performance gain exceeding 1.6% over vanilla Transformer with comparable speed.

cs.LG↗

arXiv2026

Quantitative Approximation Rates for Group Equivariant Learning

The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitative approximation rates for ReLU networks on the class of $α$-Hölder functions $f: [0,1]^N \to \mathbb{R}$. The goal of this paper is to provide similar quantitative approximation results in the context of group equivariant learning, where the learned $α$-Hölder function is known to obey certain group symmetries. While there has been much interest in the literature in understanding the universal approximation properties of equivariant models, very few quantitative approximation results are known for equivariant models. In this paper, we bridge this gap by deriving quantitative approximation rates for several prominent group-equivariant and invariant architectures. The architectures that we consider include: the permutation-invariant Deep Sets architecture; the permutation-equivariant Sumformer and Transformer architectures; joint invariance to permutations and rigid motions using invariant networks based on frame averaging; and general bi-Lipschitz invariant models. Overall, we show that equally-sized ReLU MLPs and equivariant architectures are equally expressive over equivariant functions. Thus, hard-coding equivariance does not result in a loss of expressivity or approximation power in these models.

cs.LG↗