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 1,189 records · Page 66Linked to original sources

arXiv2023

Self-Supervised Graph Transformer for Deepfake Detection

Deepfake detection methods have shown promising results in recognizing forgeries within a given dataset, where training and testing take place on the in-distribution dataset. However, their performance deteriorates significantly when presented with unseen samples. As a result, a reliable deepfake detection system must remain impartial to forgery types, appearance, and quality for guaranteed generalizable detection performance. Despite various attempts to enhance cross-dataset generalization, the problem remains challenging, particularly when testing against common post-processing perturbations, such as video compression or blur. Hence, this study introduces a deepfake detection framework, leveraging a self-supervised pre-training model that delivers exceptional generalization ability, withstanding common corruptions and enabling feature explainability. The framework comprises three key components: a feature extractor based on vision Transformer architecture that is pre-trained via self-supervised contrastive learning methodology, a graph convolution network coupled with a Transformer discriminator, and a graph Transformer relevancy map that provides a better understanding of manipulated regions and further explains the model's decision. To assess the effectiveness of the proposed framework, several challenging experiments are conducted, including in-data distribution performance, cross-dataset, cross-manipulation generalization, and robustness against common post-production perturbations. The results achieved demonstrate the remarkable effectiveness of the proposed deepfake detection framework, surpassing the current state-of-the-art approaches.

cs.CV↗

arXiv2024

Ultra Fast Transformers on FPGAs for Particle Physics Experiments

This work introduces a highly efficient implementation of the transformer architecture on a Field-Programmable Gate Array (FPGA) by using the \texttt{hls4ml} tool. Given the demonstrated effectiveness of transformer models in addressing a wide range of problems, their application in experimental triggers within particle physics becomes a subject of significant interest. In this work, we have implemented critical components of a transformer model, such as multi-head attention and softmax layers. To evaluate the effectiveness of our implementation, we have focused on a particle physics jet flavor tagging problem, employing a public dataset. We recorded latency under 2 $μ$s on the Xilinx UltraScale+ FPGA, which is compatible with hardware trigger requirements at the CERN Large Hadron Collider experiments.

cs.LG↗

arXiv2024

GPT on a Quantum Computer

Large Language Models (LLMs) such as ChatGPT have transformed how we interact with and understand the capabilities of Artificial Intelligence (AI). However, the intersection of LLMs with the burgeoning field of Quantum Machine Learning (QML) is only in its nascent stages. This paper presents an exploration of this niche by detailing a comprehensive framework for implementing the foundational Transformer architecture -- integral to ChatGPT -- within a quantum computing paradigm. We meticulously design quantum circuits that implement adapted versions of the transformer's core components and the generative pre-training phase. By integrating quantum computing with LLMs, we aspire to open new avenues for research in QML and contribute to the ongoing evolution of AI technologies.

quant-ph↗

arXiv2025

Texture, Shape, Order, and Relation Matter: A New Transformer Design for Sequential DeepFake Detection

Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures. However, these methods lack dedicated design and consequently result in limited performance. As such, this paper describes a new Transformer design, called {TSOM}, by exploring three perspectives: Texture, Shape, and Order of Manipulations. Our method features four major improvements: \ding{182} we describe a new texture-aware branch that effectively captures subtle manipulation traces with a Diversiform Pixel Difference Attention module. \ding{183} Then we introduce a Multi-source Cross-attention module to seek deep correlations among spatial and sequential features, enabling effective modeling of complex manipulation traces. \ding{184} To further enhance the cross-attention, we describe a Shape-guided Gaussian mapping strategy, providing initial priors of the manipulation shape. \ding{185} Finally, observing that the subsequent manipulation in a sequence may influence traces left in the preceding one, we intriguingly invert the prediction order from forward to backward, leading to notable gains as expected. Building upon TSOM, we introduce an extended method, {TSOM++}, which additionally explores Relation of manipulations: \ding{186} we propose a new sequential contrastive learning scheme to capture relationships between various manipulation types in sequence, further enhancing the detection of manipulation traces. We conduct extensive experiments in comparison with several state-of-the-art methods, demonstrating the superiority of our method. The code has been released at https://github.com/OUC-VAS/TSOM.

cs.CV↗

arXiv2025

Does learning the right latent variables necessarily improve in-context learning?

Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting avenues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data factorizes: examples are independent given a task latent that generates the data, e.g., linear coefficients. While an optimal predictor leverages this factorization by inferring task latents, it is unclear if Transformers implicitly do so or if they instead exploit heuristics and statistical shortcuts enabled by attention layers. Both scenarios have inspired active ongoing work. In this paper, we systematically investigate the effect of explicitly inferring task latents. We minimally modify the Transformer architecture with a bottleneck designed to prevent shortcuts in favor of more structured solutions, and then compare performance against standard Transformers across various ICL tasks. Contrary to intuition and some recent works, we find little discernible difference between the two; biasing towards task-relevant latent variables does not lead to better out-of-distribution performance, in general. Curiously, we find that while the bottleneck effectively learns to extract latent task variables from context, downstream processing struggles to utilize them for robust prediction. Our study highlights the intrinsic limitations of Transformers in achieving structured ICL solutions that generalize, and shows that while inferring the right latents aids interpretability, it is not sufficient to alleviate this problem.

cs.LG↗

arXiv2024

CAF-YOLO: A Robust Framework for Multi-Scale Lesion Detection in Biomedical Imagery

Object detection is of paramount importance in biomedical image analysis, particularly for lesion identification. While current methodologies are proficient in identifying and pinpointing lesions, they often lack the precision needed to detect minute biomedical entities (e.g., abnormal cells, lung nodules smaller than 3 mm), which are critical in blood and lung pathology. To address this challenge, we propose CAF-YOLO, based on the YOLOv8 architecture, a nimble yet robust method for medical object detection that leverages the strengths of convolutional neural networks (CNNs) and transformers. To overcome the limitation of convolutional kernels, which have a constrained capacity to interact with distant information, we introduce an attention and convolution fusion module (ACFM). This module enhances the modeling of both global and local features, enabling the capture of long-term feature dependencies and spatial autocorrelation. Additionally, to improve the restricted single-scale feature aggregation inherent in feed-forward networks (FFN) within transformer architectures, we design a multi-scale neural network (MSNN). This network improves multi-scale information aggregation by extracting features across diverse scales. Experimental evaluations on widely used datasets, such as BCCD and LUNA16, validate the rationale and efficacy of CAF-YOLO. This methodology excels in detecting and precisely locating diverse and intricate micro-lesions within biomedical imagery. Our codes are available at https://github.com/xiaochen925/CAF-YOLO.

cs.CV↗

arXiv2025

How Redundant Is the Transformer Stack in Speech Representation Models?

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection. Recent studies on transformer models revealed a high redundancy between layers and the potential for significant pruning, which we will investigate here for transformer-based speech representation models. We perform a detailed analysis of layer similarity in speech representation models using three similarity metrics: cosine similarity, centered kernel alignment, and mutual nearest-neighbor alignment. Our findings reveal a block-like structure of high similarity, suggesting two main processing steps and significant redundancy of layers. We demonstrate the effectiveness of pruning transformer-based speech representation models without the need for post-training, achieving up to 40% reduction in transformer layers while maintaining over 95% of the model's predictive capacity. Furthermore, we employ a knowledge distillation method to substitute the entire transformer stack with mimicking layers, reducing the network size 95-98% and the inference time by up to 94%. This substantial decrease in computational load occurs without considerable performance loss, suggesting that the transformer stack is almost completely redundant for downstream applications of speech representation models.

eess.AS↗

arXiv2026

MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers

In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and corresponding computational complexity are constantly scaled up in pursuit of higher performance. In this work, we present MemoryFormer, a novel transformer architecture which significantly reduces the computational complexity (FLOPs) from a new perspective. We eliminate nearly all the computations of the transformer model except for the necessary computation required by the multi-head attention operation. This is made possible by utilizing an alternative method for feature transformation to replace the linear projection of fully-connected layers. Specifically, we first construct a group of in-memory lookup tables that store a large amount of discrete vectors to replace the weight matrix used in linear projection. We then use a hash algorithm to retrieve a correlated subset of vectors dynamically based on the input embedding. The retrieved vectors combined together will form the output embedding, which provides an estimation of the result of matrix multiplication operation in a fully-connected layer. Compared to conducting matrix multiplication, retrieving data blocks from memory is a much cheaper operation which requires little computations. We train MemoryFormer from scratch and conduct extensive experiments on various benchmarks to demonstrate the effectiveness of the proposed model.

cs.CL↗

arXiv2025

From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models

We propose a novel spectral generative modeling framework for natural language processing that jointly learns a global time varying Fourier dictionary and per token mixing coefficients, replacing the ubiquitous self attention mechanism in transformer architectures. By enforcing reconstruction losses in both the time domain (embedding reconstruction) and the frequency domain (via Short Time Fourier Transform magnitude matching) alongside a standard language modeling objective, and fitting a Gaussian Mixture Model (GMM) prior over the learned mixing vectors, our approach achieves competitive perplexity and generation quality on standard benchmarks such as WikiText2 and Penn Treebank. In contrast to the quadratic computation complexity of self attention, our method operates with linear complexity, delivering substantial efficiency gains. We demonstrate that spectral dictionary models can achieve competitive performance compared to transformer baselines while significantly reducing inference latency and memory footprint, offering a compelling alternative for scalable language modeling.

cs.CL↗

arXiv2025

SafeClick: Error-Tolerant Interactive Segmentation of Any Medical Volumes via Hierarchical Expert Consensus

Foundation models for volumetric medical image segmentation have emerged as powerful tools in clinical workflows, enabling radiologists to delineate regions of interest through intuitive clicks. While these models demonstrate promising capabilities in segmenting previously unseen anatomical structures, their performance is strongly influenced by prompt quality. In clinical settings, radiologists often provide suboptimal prompts, which affects segmentation reliability and accuracy. To address this limitation, we present SafeClick, an error-tolerant interactive segmentation approach for medical volumes based on hierarchical expert consensus. SafeClick operates as a plug-and-play module compatible with foundation models including SAM 2 and MedSAM 2. The framework consists of two key components: a collaborative expert layer (CEL) that generates diverse feature representations through specialized transformer modules, and a consensus reasoning layer (CRL) that performs cross-referencing and adaptive integration of these features. This architecture transforms the segmentation process from a prompt-dependent operation to a robust framework capable of producing accurate results despite imperfect user inputs. Extensive experiments across 15 public datasets demonstrate that our plug-and-play approach consistently improves the performance of base foundation models, with particularly significant gains when working with imperfect prompts. The source code is available at https://github.com/yifangao112/SafeClick.

eess.IV↗

arXiv2025

Transformers are Graph Neural Networks

We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We show how Transformers can be viewed as message passing GNNs operating on fully connected graphs of tokens, where the self-attention mechanism capture the relative importance of all tokens w.r.t. each-other, and positional encodings provide hints about sequential ordering or structure. Thus, Transformers are expressive set processing networks that learn relationships among input elements without being constrained by apriori graphs. Despite this mathematical connection to GNNs, Transformers are implemented via dense matrix operations that are significantly more efficient on modern hardware than sparse message passing. This leads to the perspective that Transformers are GNNs currently winning the hardware lottery.

cs.LG↗

arXiv2025

Reinforcement Learning in hyperbolic space for multi-step reasoning

Multi-step reasoning is a fundamental challenge in artificial intelligence, with applications ranging from mathematical problem-solving to decision-making in dynamic environments. Reinforcement Learning (RL) has shown promise in enabling agents to perform multi-step reasoning by optimizing long-term rewards. However, conventional RL methods struggle with complex reasoning tasks due to issues such as credit assignment, high-dimensional state representations, and stability concerns. Recent advancements in Transformer architectures and hyperbolic geometry have provided novel solutions to these challenges. This paper introduces a new framework that integrates hyperbolic Transformers into RL for multi-step reasoning. The proposed approach leverages hyperbolic embeddings to model hierarchical structures effectively. We present theoretical insights, algorithmic details, and experimental results that include Frontier Math and nonlinear optimal control problems. Compared to RL with vanilla transformer, the hyperbolic RL largely improves accuracy by (32%~44%) on FrontierMath benchmark, (43%~45%) on nonlinear optimal control benchmark, while achieving impressive reduction in computational time by (16%~32%) on FrontierMath benchmark, (16%~17%) on nonlinear optimal control benchmark. Our work demonstrates the potential of hyperbolic Transformers in reinforcement learning, particularly for multi-step reasoning tasks that involve hierarchical structures.

cs.LG↗

arXiv2025

GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research

Transformers have become the foundation for a wide range of state--of--the--art models across natural language processing, computer vision, and other machine learning domains. Despite their widespread deployment, the robustness of these models under fault conditions remains underexplored. We present GoldenTransformer, a modular and extensible fault injection framework designed to evaluate the resiliency of Large Language Models to induced hardware faults. GoldenTransformer offers a unified Python-based platform for injecting diverse classes of faults--such as weight corruption, activation injections, and attention--level disruptions--into pretrained transformer--based models. Inspired by the GoldenEye simulator for DNNs, our framework focuses on the unique challenges of working with large transformer architectures, including considerations such as structural complexity, latent dependencies, and nonuniform layer definitions. GoldenTransformer is built atop PyTorch and HuggingFace Transformers, and it supports experiment reproducibility, metric logging, and visualization out of the box. We detail the technical design and use of GoldenTransformer and demonstrate through several example experiments on classification and generation tasks. By enabling controlled injection of faults at multiple logical and structural points in a transformer, GoldenTransformer offers researchers and practitioners a valuable tool for model robustness analysis and for guiding dependable system design in real-world LLM applications.

cs.LG↗

arXiv2025

EfficienT-HDR: An Efficient Transformer-Based Framework via Multi-Exposure Fusion for HDR Reconstruction

Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous driving. Multi-Exposure Fusion (MEF) is a mainstream technique to achieve this goal; however, existing methods generally face the dual bottlenecks of high computational costs and ghosting artifacts, hindering their widespread deployment. To this end, this study proposes a light-weight Vision Transformer architecture designed explicitly for HDR reconstruction to overcome these limitations. This study is based on the Context-Aware Vision Transformer and begins by converting input images to the YCbCr color space to separate luminance and chrominance information. It then employs an Intersection-Aware Adaptive Fusion (IAAF) module to suppress ghosting effectively. To further achieve a light-weight design, we introduce Inverted Residual Embedding (IRE), Dynamic Tanh (DyT), and propose Enhanced Multi-Scale Dilated Convolution (E-MSDC) to reduce computational complexity at multiple levels. Our study ultimately contributes two model versions: a main version for high visual quality and a light-weight version with advantages in computational efficiency, both of which achieve an excellent balance between performance and image quality. Experimental results demonstrate that, compared to the baseline, the main version reduces FLOPS by approximately 67% and increases inference speed by more than fivefold on CPU and 2.5 times on an edge device. These results confirm that our method provides an efficient and ghost-free HDR imaging solution for edge devices, demonstrating versatility and practicality across various dynamic scenarios.

cs.CV↗

arXiv2025

Hope Speech Detection in Social Media English Corpora: Performance of Traditional and Transformer Models

The identification of hope speech has become a promised NLP task, considering the need to detect motivational expressions of agency and goal-directed behaviour on social media platforms. This proposal evaluates traditional machine learning models and fine-tuned transformers for a previously split hope speech dataset as train, development and test set. On development test, a linear-kernel SVM and logistic regression both reached a macro-F1 of 0.78; SVM with RBF kernel reached 0.77, and Naïve Bayes hit 0.75. Transformer models delivered better results, the best model achieved weighted precision of 0.82, weighted recall of 0.80, weighted F1 of 0.79, macro F1 of 0.79, and 0.80 accuracy. These results suggest that while optimally configured traditional machine learning models remain agile, transformer architectures detect some subtle semantics of hope to achieve higher precision and recall in hope speech detection, suggesting that larges transformers and LLMs could perform better in small datasets.

cs.CL↗

arXiv2025

Evaluating Adversarial Vulnerabilities in Modern Large Language Models

The recent boom and rapid integration of Large Language Models (LLMs) into a wide range of applications warrants a deeper understanding of their security and safety vulnerabilities. This paper presents a comparative analysis of the susceptibility to jailbreak attacks for two leading publicly available LLMs, Google's Gemini 2.5 Flash and OpenAI's GPT-4 (specifically the GPT-4o mini model accessible in the free tier). The research utilized two main bypass strategies: 'self-bypass', where models were prompted to circumvent their own safety protocols, and 'cross-bypass', where one model generated adversarial prompts to exploit vulnerabilities in the other. Four attack methods were employed - direct injection, role-playing, context manipulation, and obfuscation - to generate five distinct categories of unsafe content: hate speech, illegal activities, malicious code, dangerous content, and misinformation. The success of the attack was determined by the generation of disallowed content, with successful jailbreaks assigned a severity score. The findings indicate a disparity in jailbreak susceptibility between 2.5 Flash and GPT-4, suggesting variations in their safety implementations or architectural design. Cross-bypass attacks were particularly effective, indicating that an ample amount of vulnerabilities exist in the underlying transformer architecture. This research contributes a scalable framework for automated AI red-teaming and provides data-driven insights into the current state of LLM safety, underscoring the complex challenge of balancing model capabilities with robust safety mechanisms.

cs.CR↗

arXiv2024

Forensic License Plate Recognition with Compression-Informed Transformers

Forensic license plate recognition (FLPR) remains an open challenge in legal contexts such as criminal investigations, where unreadable license plates (LPs) need to be deciphered from highly compressed and/or low resolution footage, e.g., from surveillance cameras. In this work, we propose a side-informed Transformer architecture that embeds knowledge on the input compression level to improve recognition under strong compression. We show the effectiveness of Transformers for license plate recognition (LPR) on a low-quality real-world dataset. We also provide a synthetic dataset that includes strongly degraded, illegible LP images and analyze the impact of knowledge embedding on it. The network outperforms existing FLPR methods and standard state-of-the art image recognition models while requiring less parameters. For the severest degraded images, we can improve recognition by up to 8.9 percent points.

cs.CV↗

arXiv2026

TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer

Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural networks (DGNNs) utilize Transformer architectures with various encoding designs to capture sequential evolutions of dynamic graphs. However, the effectiveness and efficiency of these Transformer-based DGNNs vary significantly, highlighting the importance of properly defining the SAM on dynamic graphs and comprehensively encoding temporal and interactive dynamics without extra complex modules. In this work, we propose TIDFormer, a dynamic graph TransFormer that fully exploits Temporal and Interactive Dynamics in an efficient manner. We clarify and verify the interpretability of our proposed SAM, addressing the open problem of its uninterpretable definitions on dynamic graphs in previous works. To model the temporal and interactive dynamics, respectively, we utilize the calendar-based time partitioning information and extract informative interaction embeddings for both bipartite and non-bipartite graphs using merely the sampled first-order neighbors. In addition, we jointly model temporal and interactive features by capturing potential changes in historical interaction patterns through a simple decomposition. We conduct extensive experiments on several dynamic graph datasets to verify the effectiveness and efficiency of TIDFormer. The experimental results demonstrate that TIDFormer excels, outperforming state-of-the-art models across most datasets and experimental settings. Furthermore, TIDFormer exhibits significant efficiency advantages compared to previous Transformer-based methods.

cs.LG↗