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 307 records · Page 17Linked to original sources

arXiv2021

Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation

Session-based recommendation is an important task for e-commerce services, where a large number of users browse anonymously or may have very distinct interests for different sessions. In this paper we present one of the winning solutions for the Recommendation task of the SIGIR 2021 Workshop on E-commerce Data Challenge. Our solution was inspired by NLP techniques and consists of an ensemble of two Transformer architectures - Transformer-XL and XLNet - trained with autoregressive and autoencoding approaches. To leverage most of the rich dataset made available for the competition, we describe how we prepared multi-model features by combining tabular events with textual and image vectors. We also present a model prediction analysis to better understand the effectiveness of our architectures for the session-based recommendation.

cs.IR↗

arXiv2025

MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition

Handwritten Mathematical Expression Recognition (HMER) methods have made remarkable progress, with most existing HMER approaches based on either a hybrid CNN/RNN-based with GRU architecture or Transformer architectures. Each of these has its strengths and weaknesses. Leveraging different model structures as viewers and effectively integrating their diverse capabilities presents an intriguing avenue for exploration. This involves addressing two key challenges: 1) How to fuse these two methods effectively, and 2) How to achieve higher performance under an appropriate level of complexity. This paper proposes an efficient CNN-Transformer multi-viewer, multi-task approach to enhance the model's recognition performance. Our MMHMER model achieves 63.96%, 62.51%, and 65.46% ExpRate on CROHME14, CROHME16, and CROHME19, outperforming Posformer with an absolute gain of 1.28%, 1.48%, and 0.58%. The main contribution of our approach is that we propose a new multi-view, multi-task framework that can effectively integrate the strengths of CNN and Transformer. By leveraging the feature extraction capabilities of CNN and the sequence modeling capabilities of Transformer, our model can better handle the complexity of handwritten mathematical expressions.

cs.CV↗

arXiv2022

Boosting Urban Traffic Speed Prediction via Integrating Implicit Spatial Correlations

Urban traffic speed prediction aims to estimate the future traffic speed for improving the urban transportation services. Enormous efforts have been made on exploiting spatial correlations and temporal dependencies of traffic speed evolving patterns by leveraging explicit spatial relations (geographical proximity) through pre-defined geographical structures ({\it e.g.}, region grids or road networks). While achieving promising results, current traffic speed prediction methods still suffer from ignoring implicit spatial correlations (interactions), which cannot be captured by grid/graph convolutions. To tackle the challenge, we propose a generic model for enabling the current traffic speed prediction methods to preserve implicit spatial correlations. Specifically, we first develop a Dual-Transformer architecture, including a Spatial Transformer and a Temporal Transformer. The Spatial Transformer automatically learns the implicit spatial correlations across the road segments beyond the boundary of geographical structures, while the Temporal Transformer aims to capture the dynamic changing patterns of the implicit spatial correlations. Then, to further integrate both explicit and implicit spatial correlations, we propose a distillation-style learning framework, in which the existing traffic speed prediction methods are considered as the teacher model, and the proposed Dual-Transformer architectures are considered as the student model. The extensive experiments over three real-world datasets indicate significant improvements of our proposed framework over the existing methods.

cs.LG↗

arXiv2023

Revisiting Image Deblurring with an Efficient ConvNet

Image deblurring aims to recover the latent sharp image from its blurry counterpart and has a wide range of applications in computer vision. The Convolution Neural Networks (CNNs) have performed well in this domain for many years, and until recently an alternative network architecture, namely Transformer, has demonstrated even stronger performance. One can attribute its superiority to the multi-head self-attention (MHSA) mechanism, which offers a larger receptive field and better input content adaptability than CNNs. However, as MHSA demands high computational costs that grow quadratically with respect to the input resolution, it becomes impractical for high-resolution image deblurring tasks. In this work, we propose a unified lightweight CNN network that features a large effective receptive field (ERF) and demonstrates comparable or even better performance than Transformers while bearing less computational costs. Our key design is an efficient CNN block dubbed LaKD, equipped with a large kernel depth-wise convolution and spatial-channel mixing structure, attaining comparable or larger ERF than Transformers but with a smaller parameter scale. Specifically, we achieve +0.17dB / +0.43dB PSNR over the state-of-the-art Restormer on defocus / motion deblurring benchmark datasets with 32% fewer parameters and 39% fewer MACs. Extensive experiments demonstrate the superior performance of our network and the effectiveness of each module. Furthermore, we propose a compact and intuitive ERFMeter metric that quantitatively characterizes ERF, and shows a high correlation to the network performance. We hope this work can inspire the research community to further explore the pros and cons of CNN and Transformer architectures beyond image deblurring tasks.

cs.CV↗

arXiv2023

SpectFormer: Frequency and Attention is what you need in a Vision Transformer

Vision transformers have been applied successfully for image recognition tasks. There have been either multi-headed self-attention based (ViT \cite{dosovitskiy2020image}, DeIT, \cite{touvron2021training}) similar to the original work in textual models or more recently based on spectral layers (Fnet\cite{lee2021fnet}, GFNet\cite{rao2021global}, AFNO\cite{guibas2021efficient}). We hypothesize that both spectral and multi-headed attention plays a major role. We investigate this hypothesis through this work and observe that indeed combining spectral and multi-headed attention layers provides a better transformer architecture. We thus propose the novel Spectformer architecture for transformers that combines spectral and multi-headed attention layers. We believe that the resulting representation allows the transformer to capture the feature representation appropriately and it yields improved performance over other transformer representations. For instance, it improves the top-1 accuracy by 2\% on ImageNet compared to both GFNet-H and LiT. SpectFormer-S reaches 84.25\% top-1 accuracy on ImageNet-1K (state of the art for small version). Further, Spectformer-L achieves 85.7\% that is the state of the art for the comparable base version of the transformers. We further ensure that we obtain reasonable results in other scenarios such as transfer learning on standard datasets such as CIFAR-10, CIFAR-100, Oxford-IIIT-flower, and Standford Car datasets. We then investigate its use in downstream tasks such of object detection and instance segmentation on the MS-COCO dataset and observe that Spectformer shows consistent performance that is comparable to the best backbones and can be further optimized and improved. Hence, we believe that combined spectral and attention layers are what are needed for vision transformers.

cs.CV↗

arXiv2024

Transformer-based approach for Ethereum Price Prediction Using Crosscurrency correlation and Sentiment Analysis

The research delves into the capabilities of a transformer-based neural network for Ethereum cryptocurrency price forecasting. The experiment runs around the hypothesis that cryptocurrency prices are strongly correlated with other cryptocurrencies and the sentiments around the cryptocurrency. The model employs a transformer architecture for several setups from single-feature scenarios to complex configurations incorporating volume, sentiment, and correlated cryptocurrency prices. Despite a smaller dataset and less complex architecture, the transformer model surpasses ANN and MLP counterparts on some parameters. The conclusion presents a hypothesis on the illusion of causality in cryptocurrency price movements driven by sentiments.

cs.LG↗

arXiv2025

Scaling Laws for Online Advertisement Retrieval

The scaling law is a notable property of neural network models and has significantly propelled the development of large language models. Scaling laws hold great promise in guiding model design and resource allocation. Recent research increasingly shows that scaling laws are not limited to NLP tasks or Transformer architectures; they also apply to domains such as recommendation. However, there is still a lack of literature on scaling law research in online advertisement retrieval systems. This may be because 1) identifying the scaling law for resource cost and online revenue is often expensive in both time and training resources for industrial applications, and 2) varying settings for different systems prevent the scaling law from being applied across various scenarios. To address these issues, we propose a lightweight paradigm to identify online scaling laws of retrieval models, incorporating a novel offline metric and an offline simulation algorithm. We prove that under mild assumptions, the correlation between the novel metric and online revenue asymptotically approaches 1 and empirically validates its effectiveness. The simulation algorithm can estimate the machine cost offline. Based on the lightweight paradigm, we can identify online scaling laws for retrieval models almost exclusively through offline experiments, and quickly estimate machine costs and revenues for given model configurations. We further validate the existence of scaling laws across mainstream model architectures (e.g., Transformer, MLP, and DSSM) in our real-world advertising system. With the identified scaling laws, we demonstrate practical applications for ROI-constrained model designing and multi-scenario resource allocation in the online advertising system. To the best of our knowledge, this is the first work to study identification and application of online scaling laws for online advertisement retrieval.

cs.IR↗

arXiv2024

A Real-Time DETR Approach to Bangladesh Road Object Detection for Autonomous Vehicles

In the recent years, we have witnessed a paradigm shift in the field of Computer Vision, with the forthcoming of the transformer architecture. Detection Transformers has become a state of the art solution to object detection and is a potential candidate for Road Object Detection in Autonomous Vehicles. Despite the abundance of object detection schemes, real-time DETR models are shown to perform significantly better on inference times, with minimal loss of accuracy and performance. In our work, we used Real-Time DETR (RTDETR) object detection on the BadODD Road Object Detection dataset based in Bangladesh, and performed necessary experimentation and testing. Our results gave a mAP50 score of 0.41518 in the public 60% test set, and 0.28194 in the private 40% test set.

cs.CV↗

arXiv2026

MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs

Recent advances in biomolecular modeling have been catalyzed by models such as AlphaFold3 (AF3), which introduce science-informed changes to the transformer architecture. Unlike transformers, a defining characteristic of AF3-style models is their 3D attention over 2D pairwise representations which produces tensors whose computation and memory costs scale cubically with sequence length. As a result, despite moderate parameter counts, AF3-style models are far more expensive to train than size-equivalent transformers, and are severely constrained by GPU memory capacity. Our characterization shows 3D attention fundamentally changes the training workload, causing massive 3D attention maps, complex inter-operator dependencies, kernel fragmentation, and heavy host-side data pipelines which differ substantially from LLM training, leading to poor utilization on modern GPU systems. Moreover, existing GPU optimizations do not adequately address these challenges due to complex cross-layer inter-operator dependencies introduced by 3D attention. Motivated by these challenges, we introduce MegaFold, a novel cross-platform system for efficient training of next-generation 3D-attention protein models. MegaFold combines a memory-efficient 3D-attention kernel, a communication-efficient sharding strategy for quadratic representations, fused operator implementations for critical execution paths, and a determinism-aware host-device pipeline that eliminates preprocessing stalls. Evaluation on both NVIDIA H200 and AMD MI250 GPUs shows that MegaFold enables training with up to 3.36$\times$ longer sequence lengths on 32 GPUs while reducing end-to-end execution time by up to 1.73$\times$ (NVIDIA) and 1.62$\times$ (AMD).

q-bio.BM↗

arXiv2025

What do language models model? Transformers, automata, and the format of thought

What do large language models actually model? Do they tell us something about human capacities, or are they models of the corpus we've trained them on? I give a non-deflationary defence of the latter position. Cognitive science tells us that linguistic capabilities in humans rely supralinear formats for computation. The transformer architecture, by contrast, supports at best a linear formats for processing. This argument will rely primarily on certain invariants of the computational architecture of transformers. I then suggest a positive story about what transformers are doing, focusing on Liu et al. (2022)'s intriguing speculations about shortcut automata. I conclude with why I don't think this is a terribly deflationary story. Language is not (just) a means for expressing inner state but also a kind of 'discourse machine' that lets us make new language given appropriate context. We have learned to use this technology in one way; LLMs have also learned to use it too, but via very different means.

cs.CL↗

arXiv2026

Parallelizable memory recurrent units

With the emergence of massively parallel processing units, parallelization has become a desirable property for new sequence models. The ability to parallelize the processing of sequences with respect to the sequence length during training is one of the main factors behind the uprising of the Transformer architecture. However, Transformers lack efficiency at sequence generation, as they need to reprocess all past timesteps at every generation step. Recently, state-space models (SSMs) emerged as a more efficient alternative. These new kinds of recurrent neural networks (RNNs) keep the efficient update of the RNNs while gaining parallelization by getting rid of nonlinear dynamics (or recurrence). SSMs can reach state-of-the art performance through the efficient training of potentially very large networks, but still suffer from limited representation capabilities. In particular, SSMs cannot exhibit persistent memory, or the capacity of retaining information for an infinite duration, because of their monostability. In this paper, we introduce a new family of RNNs, the memory recurrent units (MRUs), that combine the persistent memory capabilities of nonlinear RNNs with the parallelizable computations of SSMs. These units leverage multistability as a source of persistent memory, while getting rid of transient dynamics for efficient computations. We then derive a specific implementation as proof-of-concept: the bistable memory recurrent unit (BMRU). This new RNN is compatible with the parallel scan algorithm. We show that BMRU achieves good results in tasks with long-term dependencies, and can be combined with state-space models to create hybrid networks that are parallelizable and have transient dynamics as well as persistent memory.

cs.LG↗

arXiv2026

Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation

AI coding assistants increasingly generate code alongside tests. How developers structure test code, whether inline with the implementation or in separate blocks, has traditionally been a matter of testing philosophy. We investigate whether this choice affects AI code generation quality. We conduct a large-scale empirical study (830+ generated files, 12 models, 3 providers) using SEGA, a three-dimensional evaluation framework measuring Determinism, Preservation, and Correctness. Comparing inline test syntax (Python doctests) against separated test syntax (Rust #[test] blocks) on a d-ary heap implementation, we find that: (1) inline tests yield near-perfect preservation (100%) and correctness (92-100%) across all models; (2) separated tests expose stark model-tier gaps (0-100% correctness) and independence between preservation and correctness; (3) model behavior evolves across generations, and notably one model breaks the test suppression pattern of its three predecessors; (4) mechanistic analysis on 7 open-source architectures (6 transformers and a gated-linear Recurrent Neural Network (RNN)) reveals inline test markers receive 2.8-4.4$\times$ stronger attention in 5/7 models, with causal validation via knockout and steering experiments on the 4 code-specialized transformers and RWKV-6; the co-location mechanism extends to a non-transformer architecture, suggesting the design recommendation is robust to future architectural shifts. In the Foundation Model era, test syntax structure is a software design concern: co-locating tests with implementation code produces measurably better AI-generated code. This arxiv long version includes appendices that further qualify the effect as bounded by both model capability and programming language.

cs.SE↗

arXiv2026

Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks

Many robotic tasks require short-term memory, whether it's retrieving an object that's no longer visible or turning off an appliance after a set period. Yet, most visuomotor policies trained via imitation learning rely only on immediate sensory input without using past experiences to guide decisions. We present PRISM, a transformer-based architecture for visuomotor policies to effectively use short-term memory via two key components: (i) gated attention, which filters retrieved information to suppress irrelevant details, improving performance by reducing the spurious correlations between the history and current action prediction, (ii) a hierarchical architecture that first compresses local information into compact tokens and then integrates them to capture temporally extended dependencies, improving its compute and memory footprint. Together, these mechanisms enable us to scale short-term memory in visuomotor policies for up to two minutes. To systematically evaluate memory in visuomotor control, we introduce ReMemBench -- a benchmark of eight diverse household manipulation tasks spanning four categories of short-term memory -- designed to foster general memory mechanisms rather than siloed, task-specific solutions. PRISM consistently outperforms prior works, including recurrent architectures, transformers, and their variants -- achieving an absolute improvement of 5%--12% over the strongest baseline. On the RoboCasa and LIBERO benchmarks, it achieves absolute improvements of 11%--15% over its no-memory variant and fine-tuned Vision-Language-Action baselines such as GR00T-N1-3B and OpenVLA, despite not leveraging any large-scale pretraining. Together, PRISM and ReMemBench establish a foundation for developing and evaluating short-term memory-augmented visuomotor policies that scale to long-horizon tasks. Additional materials are available at https://shahrutav.github.io/short-term-memory

cs.RO↗

arXiv2026

From Hits to Tracks: A BERT-based Tracking Model for Track Reconstruction in Drift Chambers

Track reconstruction in drift chambers is essential for momentum measurement and particle identification at electron-positron colliders. While Transformer architectures have transformed many sequence-processing domains, their application to tracking in high energy physics is still being explored. We present a model that combines a BERT encoder with a Transformer decoder to perform hit-to-track association through autoregressive sorting. The model is evaluated on the DCTracks open dataset that provides realistic drift chamber simulations with varying particle types, momenta, track multiplicities, and noise conditions. Across single-track, two-track, and multi-track samples, the model achieves high hit and track efficiencies while keeping the rates of clones and fakes very low. It also works well in the reconstruction of displaced vertices. These results show BERT-based sequence-to-sequence models as a promising approach for track reconstruction in low-background, precision-oriented experiments.

hep-ex↗

arXiv2024

Real-Time Detection of Electronic Components in Waste Printed Circuit Boards: A Transformer-Based Approach

Critical Raw Materials (CRMs) such as copper, manganese, gallium, and various rare earths have great importance for the electronic industry. To increase the concentration of individual CRMs and thus make their extraction from Waste Printed Circuit Boards (WPCBs) convenient, we have proposed a practical approach that involves selective disassembling of the different types of electronic components from WPCBs using mechatronic systems guided by artificial vision techniques. In this paper we evaluate the real-time accuracy of electronic component detection and localization of the Real-Time DEtection TRansformer model architecture. Transformers have recently become very popular for the extraordinary results obtained in natural language processing and machine translation. Also in this case, the transformer model achieves very good performances, often superior to those of the latest state of the art object detection and localization models YOLOv8 and YOLOv9.

cs.CV↗

arXiv2026

Designing Transformers for Continuous Diffusion Language Models

Continuous diffusion language models (CDLMs) offer an alternative approach to parallel language generation; however, most existing studies directly use transformer architectures from either causal large language models (LLMs) or Diffusion Transformers (DiTs) for image generation, which were not optimized for CDLMs. In this paper, we conduct a systematic study on Transformer architectures for CDLMs and introduce Language Diffusion Transformer (LangDiT), combining feature and query-key normalization, wider noise conditioning, likelihood-shortcut gradient routing and calibration, and confidence-gated training self-conditioning. LangDiT significantly reduces generation perplexity in matched LangFlow comparisons, establishing a new state of the art in continuous language generation across different model formulations. Using LangFlow as a representative CDLM, LangDiT as a plug-and-play backbone leads to a new state-of-the-art model with a generation perplexity (GenPPL) of 21.72 using 1024 NFEs and 44.72 GenPPL using 128 NFEs on the unconditional generation of 1024-token sequences on the OpenWebText dataset. When adapted to Plaid-style CDLM formulations, LangDiT results in a new leading GenPPL of 11.33 using 1024 denoising NFEs, and 27.51 GenPPL using 128 denoising NFEs. These gains are achieved while retaining each model's underlying representation, training objective, and inference sampler, isolating transformer architecture as a fundamental source of improvement. Our study identifies architectural design as an important source of improvement in continuous diffusion language models.

cs.AI↗

arXiv2026

The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling

Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct components: a token stream updated by attention and a context stream updated by feed-forward networks. Information flow between attention heads is controlled through a hierarchy of mixing strategies, from fully independent (maximum interpretability) to dense (standard transformer behavior). This design exposes a tunable tradeoff between interpretability and performance. We measure this tradeoff on language modeling tasks at 29M parameters. Fully independent head mixing increases validation loss by 8\% relative to dense baselines. The recommended Kronecker mixing strategy, which permits scalar communication between heads while preserving within-head structure, costs only 2.5\%. All configurations maintain functional generation under attention amplification (scaling logits by factors up to 16 at inference time), with degradation ranging from 16\% to 27\%. This robustness suggests the architectures learn discrete algorithms that operate independently of soft probabilistic mixing. The architecture provides a foundation for interpretable language models where internal structure is exposed by design. \footnote{This work was partially supported by DARPA Contract HR001125C0302.}

cs.CL↗

arXiv2024

Lateralization MLP: A Simple Brain-inspired Architecture for Diffusion

The Transformer architecture has dominated machine learning in a wide range of tasks. The specific characteristic of this architecture is an expensive scaled dot-product attention mechanism that models the inter-token interactions, which is known to be the reason behind its success. However, such a mechanism does not have a direct parallel to the human brain which brings the question if the scaled-dot product is necessary for intelligence with strong expressive power. Inspired by the lateralization of the human brain, we propose a new simple but effective architecture called the Lateralization MLP (L-MLP). Stacking L-MLP blocks can generate complex architectures. Each L-MLP block is based on a multi-layer perceptron (MLP) that permutes data dimensions, processes each dimension in parallel, merges them, and finally passes through a joint MLP. We discover that this specific design outperforms other MLP variants and performs comparably to a transformer-based architecture in the challenging diffusion task while being highly efficient. We conduct experiments using text-to-image generation tasks to demonstrate the effectiveness and efficiency of L-MLP. Further, we look into the model behavior and discover a connection to the function of the human brain. Our code is publicly available: \url{https://github.com/zizhao-hu/L-MLP}

cs.CV↗