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 919 records · Page 51Linked to original sources

arXiv2024

Trackastra: Transformer-based cell tracking for live-cell microscopy

Cell tracking is a ubiquitous image analysis task in live-cell microscopy. Unlike multiple object tracking (MOT) for natural images, cell tracking typically involves hundreds of similar-looking objects that can divide in each frame, making it a particularly challenging problem. Current state-of-the-art approaches follow the tracking-by-detection paradigm, i.e. first all cells are detected per frame and successively linked in a second step to form biologically consistent cell tracks. Linking is commonly solved via discrete optimization methods, which require manual tuning of hyperparameters for each dataset and are therefore cumbersome to use in practice. Here we propose Trackastra, a general purpose cell tracking approach that uses a simple transformer architecture to directly learn pairwise associations of cells within a temporal window from annotated data. Importantly, unlike existing transformer-based MOT pipelines, our learning architecture also accounts for dividing objects such as cells and allows for accurate tracking even with simple greedy linking, thus making strides towards removing the requirement for a complex linking step. The proposed architecture operates on the full spatio-temporal context of detections within a time window by avoiding the computational burden of processing dense images. We show that our tracking approach performs on par with or better than highly tuned state-of-the-art cell tracking algorithms for various biological datasets, such as bacteria, cell cultures and fluorescent particles. We provide code at https://github.com/weigertlab/trackastra.

cs.CV↗

arXiv2024

Mamba for Scalable and Efficient Personalized Recommendations

In this effort, we propose using the Mamba for handling tabular data in personalized recommendation systems. We present the \textit{FT-Mamba} (Feature Tokenizer\,$+$\,Mamba), a novel hybrid model that replaces Transformer layers with Mamba layers within the FT-Transformer architecture, for handling tabular data in personalized recommendation systems. The \textit{Mamba model} offers an efficient alternative to Transformers, reducing computational complexity from quadratic to linear by enhancing the capabilities of State Space Models (SSMs). FT-Mamba is designed to improve the scalability and efficiency of recommendation systems while maintaining performance. We evaluate FT-Mamba in comparison to a traditional Transformer-based model within a Two-Tower architecture on three datasets: Spotify music recommendation, H\&M fashion recommendation, and vaccine messaging recommendation. Each model is trained on 160,000 user-action pairs, and performance is measured using precision (P), recall (R), Mean Reciprocal Rank (MRR), and Hit Ratio (HR) at several truncation values. Our results demonstrate that FT-Mamba outperforms the Transformer-based model in terms of computational efficiency while maintaining or exceeding performance across key recommendation metrics. By leveraging Mamba layers, FT-Mamba provides a scalable and effective solution for large-scale personalized recommendation systems, showcasing the potential of the Mamba architecture to enhance both efficiency and accuracy.

cs.IR↗

arXiv2026

Relational Attention for Data-Efficient Language Modeling

We present Relational BabyLM, a system submission to the BabyLM 2026 challenge that combines two cognitively motivated inductive biases in a single decoder-only Transformer. Architecturally, we replace standard self-attention with a Dual Attention Transformer (DAT), which separates the routing of object-level ("sensory") lexical features from structural/relational information (Altabaa and Lafferty, 2025; Altabaa et al., 2024; Webb et al., 2024; Kerg et al., 2022; Webb et al., 2021). Relational attention (RA) disentangled from self-attention greatly increases data efficiency and out-of-training-sample generalization on purely relational tasks, but language modeling requires object-level and relational information to be integrated as well as disentangled, and RA-based LMs have remained largely unexplored. BabyLM's data-constrained training and comprehensive evaluation is an ideal testing ground for whether that data efficiency transfers. As a training intervention, we add a Next-Latent Prediction (NextLat; Teoh et al. 2026) objective that encourages hidden states to compress history incrementally into a dense belief state. Architecture is the dominant factor for structural linguistic generalization; the objective is secondary but still significant. DAT's three relational attention types (full RA vs. the simpler RCA and DisRCA variants) are largely interchangeable at 10M words; full RA pulls ahead at 100M. We also introduce a novel symbol-retrieval mechanism (RoPE-based, as opposed to learned, relative symbols) that matches learned symbol libraries while adding no parameters. On the strict (100M-word) track, our best model ranks 6th of 55 overall and 3rd of 55 on the leaderboard's NLP-task subset at the time of writing; our two strongest models outperform the GPT-2 baseline on most benchmarks, with one attaining the highest EWoK score among strict-track entries.

cs.CL↗

arXiv2026

On-Policy Attention Linearization

Hybrid transformer architectures that replace most softmax attention layers with linear attention offer transformer-level quality at a fraction of the memory cost. Rather than pretraining such models, a growing body of work distills them from already trained full-attention transformers. However, these distilled models often collapse on long-context retrieval and reasoning tasks, particularly when operating in thinking mode, where the efficiency gains of hybrid architectures matter most. Since linear attention layers must compress context into a fixed-size state, their errors compound over long sequences. As off-policy distillation never teaches the student model to recover from this drift, tasks that necessitate longer sequence lengths become especially challenging. We introduce On-Policy Attention Linearization (OPAL) in which the hybrid attention student samples its own long-context trajectories and receives dense supervision from the frozen full-attention teacher. Applying OPAL to Qwen3-4B and MiMo-7B-RL-0530, we recover $87$--$94\%$ of full-attention performance on commonsense reasoning, $100\%$ on needle-in-a-haystack (NIAH) retrieval, and $83$--$93\%$ on mathematical reasoning with only 3B training tokens. We achieve these results without supervised fine-tuning (SFT) or reinforcement learning with verifiable rewards (RLVR). Compared with the strongest prior linearization method, which recovers $68\%$ of its teacher's retrieval performance and $21.6\%$ absolute average mathematical reasoning accuracy, OPAL fully recovers retrieval and achieves $67.6$--$72.2\%$ on math reasoning.

cs.LG↗

arXiv2025

A Survey of RWKV

The Receptance Weighted Key Value (RWKV) model offers a novel alternative to the Transformer architecture, merging the benefits of recurrent and attention-based systems. Unlike conventional Transformers, which depend heavily on self-attention, RWKV adeptly captures long-range dependencies with minimal computational demands. By utilizing a recurrent framework, RWKV addresses some computational inefficiencies found in Transformers, particularly in tasks with long sequences. RWKV has recently drawn considerable attention for its robust performance across multiple domains. Despite its growing popularity, no systematic review of the RWKV model exists. This paper seeks to fill this gap as the first comprehensive review of the RWKV architecture, its core principles, and its varied applications, such as natural language generation, natural language understanding, and computer vision. We assess how RWKV compares to traditional Transformer models, highlighting its capability to manage long sequences efficiently and lower computational costs. Furthermore, we explore the challenges RWKV encounters and propose potential directions for future research and advancement. We consistently maintain the related open-source materials at: https://github.com/MLGroupJLU/RWKV-Survey.

cs.CL↗

arXiv2024

Quantum-Classical Sentiment Analysis

In this study, we initially investigate the application of a hybrid classical-quantum classifier (HCQC) for sentiment analysis, comparing its performance against the classical CPLEX classifier and the Transformer architecture. Our findings indicate that while the HCQC underperforms relative to the Transformer in terms of classification accuracy, but it requires significantly less time to converge to a reasonably good approximate solution. This experiment also reveals a critical bottleneck in the HCQC, whose architecture is partially undisclosed by the D-Wave property. To address this limitation, we propose a novel algorithm based on the algebraic decomposition of QUBO models, which enhances the time the quantum processing unit can allocate to problem-solving tasks.

cs.AI↗

arXiv2020

Sparse Graph to Sequence Learning for Vision Conditioned Long Textual Sequence Generation

Generating longer textual sequences when conditioned on the visual information is an interesting problem to explore. The challenge here proliferate over the standard vision conditioned sentence-level generation (e.g., image or video captioning) as it requires to produce a brief and coherent story describing the visual content. In this paper, we mask this Vision-to-Sequence as Graph-to-Sequence learning problem and approach it with the Transformer architecture. To be specific, we introduce Sparse Graph-to-Sequence Transformer (SGST) for encoding the graph and decoding a sequence. The encoder aims to directly encode graph-level semantics, while the decoder is used to generate longer sequences. Experiments conducted with the benchmark image paragraph dataset show that our proposed achieve 13.3% improvement on the CIDEr evaluation measure when comparing to the previous state-of-the-art approach.

cs.CV↗

arXiv2021

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking

In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers. In this work, we bridge the individual video frames and explore the temporal contexts across them via a transformer architecture for robust object tracking. Different from classic usage of the transformer in natural language processing tasks, we separate its encoder and decoder into two parallel branches and carefully design them within the Siamese-like tracking pipelines. The transformer encoder promotes the target templates via attention-based feature reinforcement, which benefits the high-quality tracking model generation. The transformer decoder propagates the tracking cues from previous templates to the current frame, which facilitates the object searching process. Our transformer-assisted tracking framework is neat and trained in an end-to-end manner. With the proposed transformer, a simple Siamese matching approach is able to outperform the current top-performing trackers. By combining our transformer with the recent discriminative tracking pipeline, our method sets several new state-of-the-art records on prevalent tracking benchmarks.

cs.CV↗

arXiv2024

AAformer: Auto-Aligned Transformer for Person Re-Identification

In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-based methods only locate the human parts coarsely, or rely on pretrained human parsing models and fail in locating the identifiable nonhuman parts (e.g., knapsack). In this article, we introduce an alignment scheme in transformer architecture for the first time and propose the auto-aligned transformer (AAformer) to automatically locate both the human parts and nonhuman ones at patch level. We introduce the "Part tokens ([PART]s)", which are learnable vectors, to extract part features in the transformer. A [PART] only interacts with a local subset of patches in self-attention and learns to be the part representation. To adaptively group the image patches into different subsets, we design the auto-alignment. Auto-alignment employs a fast variant of optimal transport (OT) algorithm to online cluster the patch embeddings into several groups with the [PART]s as their prototypes. AAformer integrates the part alignment into the self-attention and the output [PART]s can be directly used as part features for retrieval. Extensive experiments validate the effectiveness of [PART]s and the superiority of AAformer over various state-of-the-art methods.

cs.CV↗

arXiv2022

PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion

The Transformer architecture has witnessed a rapid development in recent years, outperforming the CNN architectures in many computer vision tasks, as exemplified by the Vision Transformers (ViT) for image classification. However, existing visual transformer models aim to extract semantic information for high-level tasks, such as classification and detection.These methods ignore the importance of the spatial resolution of the input image, thus sacrificing the local correlation information of neighboring pixels. In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues.Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations. In addition, we construct a Pyramid Transformer to effectively extract the non-local information from the entire image. After obtaining a set of multi-scale, multi-dimensional, and multi-angle features of the original image, we design the image reconstruction network to ensure that the features can be reconstructed into the original input. To validate the effectiveness, we apply the proposed Patch Pyramid Transformer to image fusion tasks. The experimental results demonstrate its superior performance, compared to the state-of-the-art fusion approaches, achieving the best results on several evaluation indicators. Thanks to the underlying representational capacity of the PPT network, it can directly be applied to different image fusion tasks without redesigning or retraining the network.

cs.CV↗

arXiv2023

AVSegFormer: Audio-Visual Segmentation with Transformer

The combination of audio and vision has long been a topic of interest in the multi-modal community. Recently, a new audio-visual segmentation (AVS) task has been introduced, aiming to locate and segment the sounding objects in a given video. This task demands audio-driven pixel-level scene understanding for the first time, posing significant challenges. In this paper, we propose AVSegFormer, a novel framework for AVS tasks that leverages the transformer architecture. Specifically, we introduce audio queries and learnable queries into the transformer decoder, enabling the network to selectively attend to interested visual features. Besides, we present an audio-visual mixer, which can dynamically adjust visual features by amplifying relevant and suppressing irrelevant spatial channels. Additionally, we devise an intermediate mask loss to enhance the supervision of the decoder, encouraging the network to produce more accurate intermediate predictions. Extensive experiments demonstrate that AVSegFormer achieves state-of-the-art results on the AVS benchmark. The code is available at https://github.com/vvvb-github/AVSegFormer.

cs.CV↗

arXiv2026

Introduction to Transformers: an NLP Perspective

Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes a description of the standard Transformer architecture, a series of model refinements, and common applications. Given that Transformers and related deep learning techniques might be evolving in ways we have never seen, we cannot dive into all the model details or cover all the technical areas. Instead, we focus on just those concepts that are helpful for gaining a good understanding of Transformers and their variants. We also summarize the key ideas that impact this field, thereby yielding some insights into the strengths and limitations of these models.

cs.CL↗

arXiv2024

Why transformers are obviously good models of language

Nobody knows how language works, but many theories abound. Transformers are a class of neural networks that process language automatically with more success than alternatives, both those based on neural computations and those that rely on other (e.g. more symbolic) mechanisms. Here, I highlight direct connections between the transformer architecture and certain theoretical perspectives on language. The empirical success of transformers relative to alternative models provides circumstantial evidence that the linguistic approaches that transformers embody should be, at least, evaluated with greater scrutiny by the linguistics community and, at best, considered to be the currently best available theories.

cs.CL↗

arXiv2024

Emotion-Guided Image to Music Generation

Generating music from images can enhance various applications, including background music for photo slideshows, social media experiences, and video creation. This paper presents an emotion-guided image-to-music generation framework that leverages the Valence-Arousal (VA) emotional space to produce music that aligns with the emotional tone of a given image. Unlike previous models that rely on contrastive learning for emotional consistency, the proposed approach directly integrates a VA loss function to enable accurate emotional alignment. The model employs a CNN-Transformer architecture, featuring pre-trained CNN image feature extractors and three Transformer encoders to capture complex, high-level emotional features from MIDI music. Three Transformer decoders refine these features to generate musically and emotionally consistent MIDI sequences. Experimental results on a newly curated emotionally paired image-MIDI dataset demonstrate the proposed model's superior performance across metrics such as Polyphony Rate, Pitch Entropy, Groove Consistency, and loss convergence.

cs.SD↗

arXiv2024

From Noise to Nuance: Advances in Deep Generative Image Models

Deep learning-based image generation has undergone a paradigm shift since 2021, marked by fundamental architectural breakthroughs and computational innovations. Through reviewing architectural innovations and empirical results, this paper analyzes the transition from traditional generative methods to advanced architectures, with focus on compute-efficient diffusion models and vision transformer architectures. We examine how recent developments in Stable Diffusion, DALL-E, and consistency models have redefined the capabilities and performance boundaries of image synthesis, while addressing persistent challenges in efficiency and quality. Our analysis focuses on the evolution of latent space representations, cross-attention mechanisms, and parameter-efficient training methodologies that enable accelerated inference under resource constraints. While more efficient training methods enable faster inference, advanced control mechanisms like ControlNet and regional attention systems have simultaneously improved generation precision and content customization. We investigate how enhanced multi-modal understanding and zero-shot generation capabilities are reshaping practical applications across industries. Our analysis demonstrates that despite remarkable advances in generation quality and computational efficiency, critical challenges remain in developing resource-conscious architectures and interpretable generation systems for industrial applications. The paper concludes by mapping promising research directions, including neural architecture optimization and explainable generation frameworks.

cs.CV↗

arXiv2026

Gradient Heterogeneity Complements Hessian Heterogeneity in Transformer Optimization

Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite extensive efforts, the mechanisms behind Adam's advantage over SGD in Transformer optimization are still not fully understood. In this study, we analyze the optimization of Transformer models in the fine-tuning setting through the lens of gradient heterogeneity, defined as the variation in gradient norms across parameter blocks. We provide a theoretical analysis showing that gradient heterogeneity, together with Hessian heterogeneity, degrades the convergence of gradient-based methods such as SGD, while sign-based methods are substantially less sensitive to this effect. Adam and SignSGD both perform coordinate-wise updates and are less sensitive to the scale of individual gradient coordinates than SGD. This motivates our use of SignSGD as an analytically tractable proxy for Adam-like behavior. Our analysis uses the fact that SGD and SignSGD follow steepest descent directions under different norms, and derives upper bounds on the iteration complexity with implications for learning-rate scaling for SignSGD. We further investigate the origin of gradient heterogeneity in Transformer architectures and show that it is strongly influenced by the placement of layer normalization, with Post-LN architectures exhibiting particularly pronounced heterogeneity. Experimental results from fine-tuning Transformers in both NLP and vision domains validate our theoretical analysis.

cs.LG↗

arXiv2025

Learning from Scratch: Structurally-masked Transformer for Next Generation Lib-free Simulation

This paper proposes a neural framework for power and timing prediction of multi-stage data path, distinguishing itself from traditional lib-based analytical methods dependent on driver characterization and load simplifications. To the best of our knowledge, this is the first language-based, netlist-aware neural network designed explicitly for standard cells. Our approach employs two pre-trained neural models of waveform prediction and delay estimation that directly infer transient waveforms and propagation delays from SPICE netlists, conditioned on critical physical parameters such as load capacitance, input slew, and gate size. This method accurately captures both intrinsic and coupling-induced delay effects without requiring simplification or interpolation. For multi-stage timing prediction, we implement a recursive propagation strategy where predicted waveforms from each stage feed into subsequent stages, cumulatively capturing delays across the logic chain. This approach ensures precise timing alignment and complete waveform visibility throughout complex signal pathways. The waveform prediction utilizes a hybrid CNN-Transformer architecture with netlist-aware node-level encoding, addressing traditional Transformers' fixed input dimensionality constraints. Additionally, specialized subnetworks separately handle primary delay estimation and crosstalk correction. Experimental results demonstrate SPICE-level accuracy, consistently achieving RMSE below 0.0098 across diverse industrial circuits. The proposed framework provides a scalable, structurally adaptable neural alternative to conventional power and timing engines, demonstrating high fidelity to physical circuit behaviors.

eess.SP↗

arXiv2025

Evaluating the Explainability of Vision Transformers in Medical Imaging

Understanding model decisions is crucial in medical imaging, where interpretability directly impacts clinical trust and adoption. Vision Transformers (ViTs) have demonstrated state-of-the-art performance in diagnostic imaging; however, their complex attention mechanisms pose challenges to explainability. This study evaluates the explainability of different Vision Transformer architectures and pre-training strategies - ViT, DeiT, DINO, and Swin Transformer - using Gradient Attention Rollout and Grad-CAM. We conduct both quantitative and qualitative analyses on two medical imaging tasks: peripheral blood cell classification and breast ultrasound image classification. Our findings indicate that DINO combined with Grad-CAM offers the most faithful and localized explanations across datasets. Grad-CAM consistently produces class-discriminative and spatially precise heatmaps, while Gradient Attention Rollout yields more scattered activations. Even in misclassification cases, DINO with Grad-CAM highlights clinically relevant morphological features that appear to have misled the model. By improving model transparency, this research supports the reliable and explainable integration of ViTs into critical medical diagnostic workflows.

cs.CV↗