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 1,045 records · Page 58Linked to original sources

arXiv2024

Geotokens and Geotransformers

In transformer architectures, position encoding primarily provides a sense of sequence for input tokens. While the original transformer paper's method has shown satisfactory results in general language processing tasks, there have been new proposals, such as Rotary Position Embedding (RoPE), for further improvement. This paper presents geotokens, input components for transformers, each linked to a specific geological location. Unlike typical language sequences, for these tokens, the order is not as vital as the geographical coordinates themselves. To represent the relative position in this context and to keep a balance between the real world distance and the distance in the embedding space, we design a position encoding approach drawing from the RoPE structure but tailored for spherical coordinates.

cs.CL↗

arXiv2024

Transformer Conformal Prediction for Time Series

We present a conformal prediction method for time series using the Transformer architecture to capture long-memory and long-range dependencies. Specifically, we use the Transformer decoder as a conditional quantile estimator to predict the quantiles of prediction residuals, which are used to estimate the prediction interval. We hypothesize that the Transformer decoder benefits the estimation of the prediction interval by learning temporal dependencies across past prediction residuals. Our comprehensive experiments using simulated and real data empirically demonstrate the superiority of the proposed method compared to the existing state-of-the-art conformal prediction methods.

cs.LG↗

arXiv2024

Looking Beyond The Top-1: Transformers Determine Top Tokens In Order

Understanding the inner workings of Transformers is crucial for achieving more accurate and efficient predictions. In this work, we analyze the computation performed by Transformers in the layers after the top-1 prediction has become fixed, which has been previously referred to as the "saturation event". We expand the concept of saturation events for top-k tokens, demonstrating that similar saturation events occur across language, vision, and speech models. We find that these saturation events happen in order of the corresponding tokens' ranking, i.e., the model first decides on the top ranking token, then the second highest ranking token, and so on. This phenomenon seems intrinsic to the Transformer architecture, occurring across different architectural variants (decoder-only, encoder-only, and to a lesser extent full-Transformer), and even in untrained Transformers. We propose an underlying mechanism of task transition for this sequential saturation, where task k corresponds to predicting the k-th most probable token, and the saturation events are in fact discrete transitions between the tasks. In support of this we show that it is possible to predict the current task from hidden layer embedding. Furthermore, using an intervention method we demonstrate that we can cause the model to switch from one task to the next. Finally, leveraging our findings, we introduce a novel token-level early-exit strategy, which surpasses existing methods in balancing performance and efficiency.

cs.CL↗

arXiv2025

Fine-grained Hierarchical Crop Type Classification from Integrated Hyperspectral EnMAP Data and Multispectral Sentinel-2 Time Series: A Large-scale Dataset and Dual-stream Transformer Method

Fine-grained crop type classification serves as the fundamental basis for large-scale crop mapping and plays a vital role in ensuring food security. It requires simultaneous capture of both phenological dynamics (obtained from multi-temporal satellite data like Sentinel-2) and subtle spectral variations (demanding nanometer-scale spectral resolution from hyperspectral imagery). Research combining these two modalities remains scarce currently due to challenges in hyperspectral data acquisition and crop types annotation costs. To address these issues, we construct a hierarchical hyperspectral crop dataset (H2Crop) by integrating 30m-resolution EnMAP hyperspectral data with Sentinel-2 time series. With over one million annotated field parcels organized in a four-tier crop taxonomy, H2Crop establishes a vital benchmark for fine-grained agricultural crop classification and hyperspectral image processing. We propose a dual-stream Transformer architecture that synergistically processes these modalities. It coordinates two specialized pathways: a spectral-spatial Transformer extracts fine-grained signatures from hyperspectral EnMAP data, while a temporal Swin Transformer extracts crop growth patterns from Sentinel-2 time series. The designed hierarchical classification head with hierarchical fusion then simultaneously delivers multi-level crop type classification across all taxonomic tiers. Experiments demonstrate that adding hyperspectral EnMAP data to Sentinel-2 time series yields a 4.2% average F1-scores improvement (peaking at 6.3%). Extensive comparisons also confirm our method's higher accuracy over existing deep learning approaches for crop type classification and the consistent benefits of hyperspectral data across varying temporal windows and crop change scenarios. Codes and dataset are available at https://github.com/flyakon/H2Crop.

cs.CV↗

arXiv2025

Modulo Video Recovery via Selective Spatiotemporal Vision Transformer

Conventional image sensors have limited dynamic range, causing saturation in high-dynamic-range (HDR) scenes. Modulo cameras address this by folding incident irradiance into a bounded range, yet require specialized unwrapping algorithms to reconstruct the underlying signal. Unlike HDR recovery, which extends dynamic range from conventional sampling, modulo recovery restores actual values from folded samples. Despite being introduced over a decade ago, progress in modulo image recovery has been slow, especially in the use of modern deep learning techniques. In this work, we demonstrate that standard HDR methods are unsuitable for modulo recovery. Transformers, however, can capture global dependencies and spatial-temporal relationships crucial for resolving folded video frames. Still, adapting existing Transformer architectures for modulo recovery demands novel techniques. To this end, we present Selective Spatiotemporal Vision Transformer (SSViT), the first deep learning framework for modulo video reconstruction. SSViT employs a token selection strategy to improve efficiency and concentrate on the most critical regions. Experiments confirm that SSViT produces high-quality reconstructions from 8-bit folded videos and achieves state-of-the-art performance in modulo video recovery.

cs.CV↗

arXiv2026

Scaling Autoregressive Models for Lattice Thermodynamics

Predicting how materials behave under realistic conditions requires understanding the statistical distribution of atomic configurations on crystal lattices, a problem central to alloy design, catalysis, and the study of phase transitions. Traditional Markov-chain Monte Carlo sampling suffers from slow convergence and critical slowing down near phase transitions, motivating the use of generative models that directly learn the thermodynamic distribution. Existing autoregressive models (ARMs), however, generate configurations in a fixed sequential order and incur high memory and training costs, limiting their applicability to realistic systems. Here, we develop a framework combining any-order ARMs, which generate configurations flexibly by conditioning on any known subset of lattice sites, with marginalization models (MAMs), which approximate the probability of any partial configuration in a single forward pass and substantially reduce memory requirements. This combination enables models trained on smaller lattices to be reused for sampling larger systems, while supporting expressive Transformer architectures with lattice-aware positional encodings at manageable computational cost. We demonstrate that Transformer-based any-order MAMs achieve more accurate free energies than multilayer perceptron-based ARMs on both the two-dimensional Ising model and CuAu alloys, faithfully capturing phase transitions and critical behavior. Overall, our framework scales from $10 \times 10$ to $20 \times 20$ Ising systems and from $2 \times 2 \times 4$ to $4 \times 4 \times 8$ CuAu supercells at reduced computational cost compared to conventional sampling methods.

cond-mat.stat-mech↗

arXiv2026

Approximation Error Upper and Lower Bounds for Hölder Class with Transformers

We explore the expressive power of Transformers by establishing precise approximation error upper and lower bounds for Hölder class. Specifically, a new approximation upper bound is derived for the standard Transformer architecture equipped with Softmax operators, ReLU activation functions, and residual connections. We prove that a Transformer network composed of at most $\mathcal{O}(\varepsilon^{-{d_{0}}/α})$ blocks can approximate any bounded Hölder function with $d_{0}$-dimensional input and smoothness $α\in(0,1]$ under any accuracy $\varepsilon>0$. In the case of approximation lower bounds, leveraging the VC-dimension upper bound, we are the first to rigorously prove that Transformers demand for at least $Ω(\varepsilon^{-{d_{0}}/({4α})})$ blocks to achieve the $\varepsilon$ approximation accuracy. As a final step, we extend the derived results for standard Transformers to a general regression task and establish the corresponding excess risk rates demonstrating Transformers' empirical effectiveness in real-world settings.

cs.LG↗

arXiv2026

Learning Motion Feasibility from Point Clouds in Cluttered Environments

Motion feasibility prediction plays a central role in robotics, particularly in task and motion planning and manipulation. A major bottleneck for this problem in cluttered environments is that infeasible planning attempts by Sampling-based motion planners (SBMPs) can incur substantial computational cost. Also existing approaches for infeasibility certification are limited to low-dimensional configuration spaces and often assume simplified geometric environments represented by primitive objects with known parameters. We study the complementary problem of learning motion feasibility prediction directly from raw RGB-D observations for a 7-DOF manipulator operating in realistic cluttered scenes. We introduce the first large-scale benchmark for this setting, comprising 2.7M grasp feasibility labels over 88 scanned objects and 190 cluttered tabletop scenes. We benchmark three representative classifier families spanning MLP- based, volumetric-CNN, and point-cloud-based Transformer architectures under matched training conditions. Our best model, GRASPFC-PTX (a point-cloud transformer), achieves an AUROC of 0.996 on Novel objects while providing predictions significantly faster than SBMPs.

cs.RO↗

arXiv2026

Predicate Neuron: Differentiable Quantization of Predicate Relations in Gradient-based Learning

In machine learning, symbolic reasoning approaches often rely on static architectures that hinder integration into deep neural networks and gradient-based optimization. To address this, we introduce the Native Predicate Neuron, a differentiable logic-reasoning neural module that enriches standard architectures with symbolic reasoning capabilities via first-order logic quantization. The proposed neuron models relational logic by learning to alternate between operations using a single trainable parameter. It features a tailored gradient mechanism with a dual-nature formulation: executing hard logical operations during training while maintaining differentiability for backpropagation. By quantizing both its input and choice state, the Predicate Neuron approximates continuous and non-continuous functions, effectively resolving discontinuities that standard deep learning architectures struggle with. We evaluate the Predicate Neuron across Fully-Connected, Convolutional, Recurrent, and Transformer architectures on benchmarks like MNIST and Wikitext. Results show that incorporating Predicate Neurons accelerates convergence, boosts accuracy, and lowers loss in general, with particularly strong improvements in tasks requiring monotonic reasoning or handling discontinuities. Overall, the Predicate Neuron natively integrates into standard neural networks to enable fuzzy logic operations and is available in Keras and PyTorch.

cs.LG↗

arXiv2024

Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset

Since 2018, when the Transformer architecture was introduced, Natural Language Processing has gained significant momentum with pre-trained Transformer-based models that can be fine-tuned for various tasks. Most models are pre-trained on large English corpora, making them less applicable to other languages, such as Brazilian Portuguese. In our research, we identified two models pre-trained in Brazilian Portuguese (BERTimbau and PTT5) and two multilingual models (mBERT and mT5). BERTimbau and mBERT use only the Encoder module, while PTT5 and mT5 use both the Encoder and Decoder. Our study aimed to evaluate their performance on a financial Named Entity Recognition (NER) task and determine the computational requirements for fine-tuning and inference. To this end, we developed the Brazilian Financial NER (BraFiNER) dataset, comprising sentences from Brazilian banks' earnings calls transcripts annotated using a weakly supervised approach. Additionally, we introduced a novel approach that reframes the token classification task as a text generation problem. After fine-tuning the models, we evaluated them using performance and error metrics. Our findings reveal that BERT-based models consistently outperform T5-based models. While the multilingual models exhibit comparable macro F1-scores, BERTimbau demonstrates superior performance over PTT5. In terms of error metrics, BERTimbau outperforms the other models. We also observed that PTT5 and mT5 generated sentences with changes in monetary and percentage values, highlighting the importance of accuracy and consistency in the financial domain. Our findings provide insights into the differing performance of BERT- and T5-based models for the NER task.

cs.CL↗

arXiv2026

Vision And Text Transformer For Predicting Answerability On Visual Question Answering

Answerability on Visual Question Answering is a novel and attractive task to predict answerable scores between images and questions in multi-modal data. Existing works often utilize a binary mapping from visual question answering systems into Answerability. It does not reflect the essence of this problem. Together with our consideration of Answerability in a regression task, we propose VT-Transformer, which exploits visual and textual features through Transformer architecture. Experimental results on VizWiz 2020 dataset show the effectiveness and robustness of VT-Transformer for Answerability on Visual Question Answering when comparing with competitive baselines.

cs.CV↗

arXiv2026

LOOKAT: Lookup-Optimized Key-Attention for Memory-Efficient Transformers

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to FP16 before use. We observe that attention scoring is mathematically equivalent to the inner product similarity search and we can apply some compression techniques from vector databases to compress KV-cache better. We propose LOOKAT, which applies product quantization and asymmetric distance computation, to transformer architecture by decomposing key vectors into subspaces, learning codebooks and computing attention tables via lookup tables. This transforms attention from memory-bound to compute-bound. LOOKAT achieves 64 $\times$ compression at 95.7\% output fidelity and 32 $\times$ compression at 95.0\% fidelity when tested on GPT-2. LOOKAT requires no architecture changes or training while maintaining rank correlation $ρ> 0.95$. Theoretical analysis confirms that rank correlation degrades as $O(d_k/mK)$, with guarantees validated across sequence lengths up to 1024 tokens.

cs.LG↗

arXiv2024

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention, gated convolution and recurrent models, and structured state space models (SSMs) have been developed to address Transformers' computational inefficiency on long sequences, but they have not performed as well as attention on important modalities such as language. We identify that a key weakness of such models is their inability to perform content-based reasoning, and make several improvements. First, simply letting the SSM parameters be functions of the input addresses their weakness with discrete modalities, allowing the model to selectively propagate or forget information along the sequence length dimension depending on the current token. Second, even though this change prevents the use of efficient convolutions, we design a hardware-aware parallel algorithm in recurrent mode. We integrate these selective SSMs into a simplified end-to-end neural network architecture without attention or even MLP blocks (Mamba). Mamba enjoys fast inference (5$\times$ higher throughput than Transformers) and linear scaling in sequence length, and its performance improves on real data up to million-length sequences. As a general sequence model backbone, Mamba achieves state-of-the-art performance across several modalities such as language, audio, and genomics. On language modeling, our Mamba-3B model outperforms Transformers of the same size and matches Transformers twice its size, both in pretraining and downstream evaluation.

cs.LG↗

arXiv2024

Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution

Tabular data, a prevalent data type across various domains, presents unique challenges due to its heterogeneous nature and complex structural relationships. Achieving high predictive performance and robustness in tabular data analysis holds significant promise for numerous applications. Influenced by recent advancements in natural language processing, particularly transformer architectures, new methods for tabular data modeling have emerged. Early techniques concentrated on pre-training transformers from scratch, often encountering scalability issues. Subsequently, methods leveraging pre-trained language models like BERT have been developed, which require less data and yield enhanced performance. The recent advent of large language models, such as GPT and LLaMA, has further revolutionized the field, facilitating more advanced and diverse applications with minimal fine-tuning. Despite the growing interest, a comprehensive survey of language modeling techniques for tabular data remains absent. This paper fills this gap by providing a systematic review of the development of language modeling for tabular data, encompassing: (1) a categorization of different tabular data structures and data types; (2) a review of key datasets used in model training and tasks used for evaluation; (3) a summary of modeling techniques including widely-adopted data processing methods, popular architectures, and training objectives; (4) the evolution from adapting traditional Pre-training/Pre-trained language models to the utilization of large language models; (5) an identification of persistent challenges and potential future research directions in language modeling for tabular data analysis. GitHub page associated with this survey is available at: https://github.com/lanxiang1017/Language-Modeling-on-Tabular-Data-Survey.git.

cs.CL↗

arXiv2022

Transformation Invariant Cancerous Tissue Classification Using Spatially Transformed DenseNet

In this work, we introduce a spatially transformed DenseNet architecture for transformation invariant classification of cancer tissue. Our architecture increases the accuracy of the base DenseNet architecture while adding the ability to operate in a transformation invariant way while simultaneously being simpler than other models that try to provide some form of invariance.

eess.IV↗

arXiv2026

Transformer-Based Rhythm Quantization of Performance MIDI Using Beat Annotations

Rhythm transcription is a key subtask of notation-level Automatic Music Transcription (AMT). While deep learning models have been extensively used for detecting the metrical grid in audio and MIDI performances, beat-based rhythm quantization remains largely unexplored. In this work, we introduce a novel deep learning approach for quantizing MIDI performances using a priori beat information. Our method leverages the transformer architecture to effectively process synchronized score and performance data for training a quantization model. Key components of our approach include dataset preparation, a beat-based pre-quantization method to align performance and score times within a unified framework, and a MIDI tokenizer tailored for this task. We adapt a transformer model based on the T5 architecture to meet the specific requirements of rhythm quantization. The model is evaluated using a set of score-level metrics designed for objective assessment of quantization performance. Through systematic evaluation, we optimize both data representation and model architecture. Additionally, we apply performance and score augmentations, such as transposition, note deletion, and performance-side time jitter, to enhance the model's robustness. Finally, a qualitative analysis compares our model's quantization performance against state-of-the-art probabilistic and deep-learning models on various example pieces. Our model achieves an onset F1-score of 97.3% and a note value accuracy of 83.3% on the ASAP dataset. It generalizes well across time signatures, including those not seen during training, and produces readable score output. Fine-tuning on instrument-specific datasets further improves performance by capturing characteristic rhythmic and melodic patterns. This work contributes a robust and flexible framework for beat-based MIDI quantization using transformer models.

cs.SD↗

arXiv2020

Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models

This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). We leverage PLMs to address the strong token-to-token independence assumption made in the common objective, maximum likelihood estimation, for the CQR task. In CQR benchmarks of task-oriented dialogue systems, we evaluate fine-tuned PLMs on the recently-introduced CANARD dataset as an in-domain task and validate the models using data from the TREC 2019 CAsT Track as an out-domain task. Examining a variety of architectures with different numbers of parameters, we demonstrate that the recent text-to-text transfer transformer (T5) achieves the best results both on CANARD and CAsT with fewer parameters, compared to similar transformer architectures.

cs.CL↗

arXiv2021

Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.

cs.CL↗