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 1,765 records · Page 98Linked to original sources

arXiv2023

Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs

Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited. Re-running the model each time is expensive, even with compression techniques like knowledge distillation, pruning, or quantization. Instead, we take an incremental computing approach, looking to reuse calculations as the inputs change. However, the dense connectivity of conventional architectures poses a major obstacle to incremental computation, as even minor input changes cascade through the network and restrict information reuse. To address this, we use vector quantization to discretize intermediate values in the network, which filters out noisy and unnecessary modifications to hidden neurons, facilitating the reuse of their values. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of the modified inputs. Our experiments with adapting the OPT-125M pre-trained language model demonstrate comparable accuracy on document classification while requiring 12.1X (median) fewer operations for processing sequences of atomic edits.

cs.LG↗

arXiv2025

Can Transformers overcome the lack of data in the simulation of history-dependent flows?

It is well known that the lack of information about certain variables necessary for the description of a dynamical system leads to the introduction of historical dependence (lack of Markovian character of the model) and noise. Traditionally, scientists have made up for these shortcomings by designing phenomenological variables that take into account this historical dependence (typically, conformational tensors in fluids). Often, these phenomenological variables are not easily measurable experimentally. In this work, we study to what extent Transformer architectures are able to cope with the lack of experimental data on these variables. The methodology is evaluated on three benchmark problems: a cylinder flow with no history dependence, a viscoelastic Couette flow modeled via the Oldroyd-B formalism, and a non-linear polymeric fluid described by the FENE model. Our results show that the Transformer outperforms a thermodynamically consistent, structure-preserving neural network with metriplectic bias in systems with missing experimental data, providing lower errors even in low-dimensional latent spaces. In contrast, for systems whose state variables can be fully known, the metriplectic model achieves superior performance.

physics.flu-dyn↗

arXiv2026

Empirical Scaling Laws of Quantum Vision Transformers

Quantum machine learning (QML) is a promising application of quantum computing, yet when and how practical learning models can achieve quantum advantage remains poorly understood. Even a polynomial improvement in the resources needed to attain a given predictive performance would be significant. In this work, we investigate empirical scaling laws of quantum vision transformers (QViTs), which connect QML to the transformer architecture underlying modern large language models. We ask whether QViTs exhibit scaling behavior analogous to classical models and how this behavior changes when qubit number is included alongside dataset size and model parameters. The validation losses in our numerical image-classification experiments are well described by a joint shifted power-law model in qubit number, transformer depth, and training dataset size. Expressing this fit in terms of the classical encoder parameter budget identifies a regime in which increasing the number of qubits can compensate for fewer classical encoder parameters at comparable predicted performance. This finding is consistent with earlier observations of parameter efficiency in quantum learning models and suggests a direction for exploring possible resource savings in QML.

quant-ph↗

arXiv2025

D-STGCNT: A Dense Spatio-Temporal Graph Conv-GRU Network based on transformer for assessment of patient physical rehabilitation

This paper tackles the challenge of automatically assessing physical rehabilitation exercises for patients who perform the exercises without clinician supervision. The objective is to provide a quality score to ensure correct performance and achieve desired results. To achieve this goal, a new graph-based model, the Dense Spatio-Temporal Graph Conv-GRU Network with Transformer, is introduced. This model combines a modified version of STGCN and transformer architectures for efficient handling of spatio-temporal data. The key idea is to consider skeleton data respecting its non-linear structure as a graph and detecting joints playing the main role in each rehabilitation exercise. Dense connections and GRU mechanisms are used to rapidly process large 3D skeleton inputs and effectively model temporal dynamics. The transformer encoder's attention mechanism focuses on relevant parts of the input sequence, making it useful for evaluating rehabilitation exercises. The evaluation of our proposed approach on the KIMORE and UI-PRMD datasets highlighted its potential, surpassing state-of-the-art methods in terms of accuracy and computational time. This resulted in faster and more accurate learning and assessment of rehabilitation exercises. Additionally, our model provides valuable feedback through qualitative illustrations, effectively highlighting the significance of joints in specific exercises.

eess.IV↗

arXiv2023

Graph Transformer for Recommendation

This paper presents a novel approach to representation learning in recommender systems by integrating generative self-supervised learning with graph transformer architecture. We highlight the importance of high-quality data augmentation with relevant self-supervised pretext tasks for improving performance. Towards this end, we propose a new approach that automates the self-supervision augmentation process through a rationale-aware generative SSL that distills informative user-item interaction patterns. The proposed recommender with Graph TransFormer (GFormer) that offers parameterized collaborative rationale discovery for selective augmentation while preserving global-aware user-item relationships. In GFormer, we allow the rationale-aware SSL to inspire graph collaborative filtering with task-adaptive invariant rationalization in graph transformer. The experimental results reveal that our GFormer has the capability to consistently improve the performance over baselines on different datasets. Several in-depth experiments further investigate the invariant rationale-aware augmentation from various aspects. The source code for this work is publicly available at: https://github.com/HKUDS/GFormer.

cs.IR↗

arXiv2024

Evaluating Vision Transformer Models for Visual Quality Control in Industrial Manufacturing

One of the most promising use-cases for machine learning in industrial manufacturing is the early detection of defective products using a quality control system. Such a system can save costs and reduces human errors due to the monotonous nature of visual inspections. Today, a rich body of research exists which employs machine learning methods to identify rare defective products in unbalanced visual quality control datasets. These methods typically rely on two components: A visual backbone to capture the features of the input image and an anomaly detection algorithm that decides if these features are within an expected distribution. With the rise of transformer architecture as visual backbones of choice, there exists now a great variety of different combinations of these two components, ranging all along the trade-off between detection quality and inference time. Facing this variety, practitioners in the field often have to spend a considerable amount of time on researching the right combination for their use-case at hand. Our contribution is to help practitioners with this choice by reviewing and evaluating current vision transformer models together with anomaly detection methods. For this, we chose SotA models of both disciplines, combined them and evaluated them towards the goal of having small, fast and efficient anomaly detection models suitable for industrial manufacturing. We evaluated the results of our experiments on the well-known MVTecAD and BTAD datasets. Moreover, we give guidelines for choosing a suitable model architecture for a quality control system in practice, considering given use-case and hardware constraints.

cs.CV↗

arXiv2022

DataMUX: Data Multiplexing for Neural Networks

In this paper, we introduce data multiplexing (DataMUX), a technique that enables deep neural networks to process multiple inputs simultaneously using a single compact representation. DataMUX demonstrates that neural networks are capable of generating accurate predictions over mixtures of inputs, resulting in increased throughput with minimal extra memory requirements. Our approach uses two key components -- 1) a multiplexing layer that performs a fixed linear transformation to each input before combining them to create a mixed representation of the same size as a single input, which is then processed by the base network, and 2) a demultiplexing layer that converts the base network's output back into independent representations before producing predictions for each input. We show the viability of DataMUX for different architectures (Transformers, and to a lesser extent MLPs and CNNs) across six different tasks spanning sentence classification, named entity recognition and image classification. For instance, DataMUX for Transformers can multiplex up to $20$x/$40$x inputs, achieving $11$x/$18$x increase in throughput with minimal absolute performance drops of $<2\%$ and $<4\%$ respectively on MNLI, a natural language inference task. We also provide a theoretical construction for multiplexing in self-attention networks and analyze the effect of various design elements in DataMUX.

cs.LG↗

arXiv2023

Dynamic Linear Transformer for 3D Biomedical Image Segmentation

Transformer-based neural networks have surpassed promising performance on many biomedical image segmentation tasks due to a better global information modeling from the self-attention mechanism. However, most methods are still designed for 2D medical images while ignoring the essential 3D volume information. The main challenge for 3D transformer-based segmentation methods is the quadratic complexity introduced by the self-attention mechanism \cite{vaswani2017attention}. In this paper, we propose a novel transformer architecture for 3D medical image segmentation using an encoder-decoder style architecture with linear complexity. Furthermore, we newly introduce a dynamic token concept to further reduce the token numbers for self-attention calculation. Taking advantage of the global information modeling, we provide uncertainty maps from different hierarchy stages. We evaluate this method on multiple challenging CT pancreas segmentation datasets. Our promising results show that our novel 3D Transformer-based segmentor could provide promising highly feasible segmentation performance and accurate uncertainty quantification using single annotation. Code is available https://github.com/freshman97/LinTransUNet.

cs.CV↗

arXiv2023

In-Context Learning with Many Demonstration Examples

Large pre-training language models (PLMs) have shown promising in-context learning abilities. However, due to the backbone transformer architecture, existing PLMs are bottlenecked by the memory and computational cost when scaling up to a large context size, leaving instruction tuning and in-context learning of many demonstration examples, as well as long-range language modeling under-explored. In this study, we propose a long-range language model EVALM based on an efficient transformer mechanism. EVALM is trained with 8k tokens per batch line and can test up to 256k-lengthed contexts with extrapolation, 128 times to the limit of existing PLMs (e.g. GPT3). Based on EVALM, we scale up the size of examples efficiently in both instruction tuning and in-context learning to explore the boundary of the benefits from more annotated data. Experimental results on a diverse set of tasks show that EVALM achieves 4.1% higher accuracy on average, and the average length of achieving the best accuracy score over tasks is around 12k. We find that in-context learning can achieve higher performance with more demonstrations under many-shot instruction tuning (8k), and further extending the length of instructions (16k) can further improve the upper bound of scaling in-context learning.

cs.CL↗

arXiv2025

Transformer-Driven Neural Beamforming with Imperfect CSI in Urban Macro Wireless Channels

The literature is abundant with methodologies focusing on using transformer architectures due to their prominence in wireless signal processing and their capability to capture long-range dependencies via attention mechanisms. In particular, depthwise separable convolutions enhance parameter efficiency for the process of high-dimensional data characteristics of MIMO systems. In this work, we introduce a novel unsupervised deep learning framework that integrates depthwise separable convolutions and transformers to generate beamforming weights under imperfect channel state information (CSI) for a multi-user single-input multiple-output (MU-SIMO) system in dense urban environments. The primary goal is to enhance throughput by maximizing sum-rate while ensuring reliable communication. Spectral efficiency and block error rate (BLER) are considered as performance metrics. Experiments are carried out under various conditions to compare the performance of the proposed NNBF framework against baseline methods zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) beamforming. Experimental results demonstrate the superiority of the proposed framework over the baseline techniques.

cs.IT↗

arXiv2026

Adaptive Engram Memory System for Indonesian Language Model: Generative AI Based on TOBA LM for Batak and Minang Language

This study presents TOBA-LM, a trilingual language model based on GPT-2 architecture with 1.2 billion parameters, trained on a corpus encompassing Indonesian, Batak, and Minangkabau using syllabic-agglutinative tokenization. The architecture integrates an Engram Memory mechanism, an adaptive n-gram-based memory system with a 500,000 x 768 embedding table that captures morphological dependencies through bigram and trigram pathways. Empirical results demonstrate a training efficiency of 80%, with the loss value dropping from 6.4 to 1.7996 in only 12,973 steps -- significantly faster than the conventional transformer architecture, which required over 70,000 steps to achieve comparable convergence. These findings confirm that the integration of external statistical memory substantially reduces computational requirements for developing regional language models under limited resources.

cs.CL↗

arXiv2026

Controlled Dynamics Attractor Transformer

Transformer architectures have dramatically advanced representation learning and inference in deep models through self-attention mechanisms. In parallel,associative memory (AM) frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms. However, their continuous-time inference dynamics lack the biological plausibility of classical Continuous Attractor Neural Networks (CANNs). To bridge this gap, we propose Controlled Dynamics Attractor Transformer (CDAT), which couples a mixture von Mises-Fisher (Mo-vMF) attention energy with a Hopfield refinement energy, while augmenting energy descent with a CANN-inspired excitation-inhibition modulation. CDAT instantiates a topology-constrained dynamical system whose couplings encode relational structure among tokens, thereby linking attractor-style dynamics to modern energy-based attention. We further provide a constructive dissipation analysis to formally establish their controlled inference dynamics. Benefiting from these robust and structured dynamics, CDAT achieves state-of-the-art performance across multiple benchmarks in graph anomaly detection and graph classification.

cs.LG↗

arXiv2025

Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization

Transformer architectures offer significant advantages regarding the generation of symbolic music; their capabilities for incorporating user preferences toward what they generate is being studied under many aspects. This paper studies the inclusion of predefined chord constraints in melodic harmonization, i.e., where a desired chord at a specific location is provided along with the melody as inputs and the autoregressive transformer model needs to incorporate the chord in the harmonization that it generates. The peculiarities of involving such constraints is discussed and an algorithm is proposed for tackling this task. This algorithm is called B* and it combines aspects of beam search and A* along with backtracking to force pretrained transformers to satisfy the chord constraints, at the correct onset position within the correct bar. The algorithm is brute-force and has exponential complexity in the worst case; however, this paper is a first attempt to highlight the difficulties of the problem and proposes an algorithm that offers many possibilities for improvements since it accommodates the involvement of heuristics.

cs.SD↗

arXiv2021

Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC). SAD optimizes the online inference efficiency for GEC by two innovations: 1) it aggressively decodes as many tokens as possible in parallel instead of always decoding only one token in each step to improve computational parallelism; 2) it uses a shallow decoder instead of the conventional Transformer architecture with balanced encoder-decoder depth to reduce the computational cost during inference. Experiments in both English and Chinese GEC benchmarks show that aggressive decoding could yield the same predictions as greedy decoding but with a significant speedup for online inference. Its combination with the shallow decoder could offer an even higher online inference speedup over the powerful Transformer baseline without quality loss. Not only does our approach allow a single model to achieve the state-of-the-art results in English GEC benchmarks: 66.4 F0.5 in the CoNLL-14 and 72.9 F0.5 in the BEA-19 test set with an almost 10x online inference speedup over the Transformer-big model, but also it is easily adapted to other languages. Our code is available at https://github.com/AutoTemp/Shallow-Aggressive-Decoding.

cs.CL↗

arXiv2021

StarVQA: Space-Time Attention for Video Quality Assessment

The attention mechanism is blooming in computer vision nowadays. However, its application to video quality assessment (VQA) has not been reported. Evaluating the quality of in-the-wild videos is challenging due to the unknown of pristine reference and shooting distortion. This paper presents a novel \underline{s}pace-\underline{t}ime \underline{a}ttention network fo\underline{r} the \underline{VQA} problem, named StarVQA. StarVQA builds a Transformer by alternately concatenating the divided space-time attention. To adapt the Transformer architecture for training, StarVQA designs a vectorized regression loss by encoding the mean opinion score (MOS) to the probability vector and embedding a special vectorized label token as the learnable variable. To capture the long-range spatiotemporal dependencies of a video sequence, StarVQA encodes the space-time position information of each patch to the input of the Transformer. Various experiments are conducted on the de-facto in-the-wild video datasets, including LIVE-VQC, KoNViD-1k, LSVQ, and LSVQ-1080p. Experimental results demonstrate the superiority of the proposed StarVQA over the state-of-the-art. Code and model will be available at: https://github.com/DVL/StarVQA.

cs.CV↗

arXiv2023

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

Recently, vision transformers have shown great success in a set of human reconstruction tasks such as 2D human pose estimation (2D HPE), 3D human pose estimation (3D HPE), and human mesh reconstruction (HMR) tasks. In these tasks, feature map representations of the human structural information are often extracted first from the image by a CNN (such as HRNet), and then further processed by transformer to predict the heatmaps (encodes each joint's location into a feature map with a Gaussian distribution) for HPE or HMR. However, existing transformer architectures are not able to process these feature map inputs directly, forcing an unnatural flattening of the location-sensitive human structural information. Furthermore, much of the performance benefit in recent HPE and HMR methods has come at the cost of ever-increasing computation and memory needs. Therefore, to simultaneously address these problems, we propose FeatER, a novel transformer design that preserves the inherent structure of feature map representations when modeling attention while reducing memory and computational costs. Taking advantage of FeatER, we build an efficient network for a set of human reconstruction tasks including 2D HPE, 3D HPE, and HMR. A feature map reconstruction module is applied to improve the performance of the estimated human pose and mesh. Extensive experiments demonstrate the effectiveness of FeatER on various human pose and mesh datasets. For instance, FeatER outperforms the SOTA method MeshGraphormer by requiring 5% of Params and 16% of MACs on Human3.6M and 3DPW datasets. The project webpage is https://zczcwh.github.io/feater_page/.

cs.CV↗

arXiv2025

Understanding Token-level Topological Structures in Transformer-based Time Series Forecasting

Transformer-based methods have achieved state-of-the-art performance in time series forecasting (TSF) by capturing positional and semantic topological relationships among input tokens. However, it remains unclear whether existing Transformers fully leverage the intrinsic topological structure among tokens throughout intermediate layers. Through empirical and theoretical analyses, we identify that current Transformer architectures progressively degrade the original positional and semantic topology of input tokens as the network deepens, thus limiting forecasting accuracy. Furthermore, our theoretical results demonstrate that explicitly enforcing preservation of these topological structures within intermediate layers can tighten generalization bounds, leading to improved forecasting performance. Motivated by these insights, we propose the Topology Enhancement Method (TEM), a novel Transformer-based TSF method that explicitly and adaptively preserves token-level topology. TEM consists of two core modules: 1) the Positional Topology Enhancement Module (PTEM), which injects learnable positional constraints to explicitly retain original positional topology; 2) the Semantic Topology Enhancement Module (STEM), which incorporates a learnable similarity matrix to preserve original semantic topology. To determine optimal injection weights adaptively, TEM employs a bi-level optimization strategy. The proposed TEM is a plug-and-play method that can be integrated with existing Transformer-based TSF methods. Extensive experiments demonstrate that integrating TEM with a variety of existing methods significantly improves their predictive performance, validating the effectiveness of explicitly preserving original token-level topology. Our code is publicly available at: \href{https://github.com/jlu-phyComputer/TEM}{https://github.com/jlu-phyComputer/TEM}.

cs.AI↗

arXiv2025

Distillation versus Contrastive Learning: How to Train Your Rerankers

Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge from a larger reranker). While both have been studied extensively, a clear comparison of their effectiveness for training cross-encoder rerankers under practical conditions is needed. This paper empirically compares these strategies by training rerankers of different sizes (0.5B, 1.5B, 3B, 7B) and architectures (Transformer, Recurrent) using both methods on the same data, with a strong contrastive learning model acting as the distillation teacher. Our results show that knowledge distillation generally yields better in-domain and out-of-domain ranking performance than contrastive learning when distilling from a more performant teacher model. This finding is consistent across student model sizes and architectures. However, distilling from a teacher of the same capacity does not provide the same advantage, particularly for out-of-domain tasks. These findings offer practical guidance for choosing a training strategy based on available teacher models. We recommend using knowledge distillation to train smaller rerankers if a larger, more performant teacher is accessible; in its absence, contrastive learning remains a robust baseline. Our code implementation is made available to facilitate reproducbility.

cs.CL↗