Downscaled models outperform larger ones on GLUE tasks.
problem Difficulty in attributing performance changes to specific factors in large language models.
method Pre-trained down-scaled versions of Transformer-based architectures on a common corpus, benchmarked on GLUE tasks.
result MLM + NSP (BERT-style) consistently outperforms other objectives.
Study compares LSTM and Transformer models in financial time series prediction.
problem Comparing LSTM and Transformer models for financial time series prediction.
method Various LSTM-based and Transformer-based models compared on financial tasks; DLSTM and new Transformer architecture designed.
result Transformer-based models show limited advantage in absolute price sequence prediction, while LSTM-based models perform better on difference sequences.
Recently, Transformer has gained success in automatic speech recognition (ASR) field. However, it is challenging to deploy a Transformer-based end-to-end (E2E) model for online speech recognition. In this paper, we propose the Transformer-based online CTC/attention E2E ASR architecture, which contains the chunk self-at…
Transformer predicts Ethereum prices using cross-currency correlation and sentiment analysis.
problem Predicting Ethereum cryptocurrency prices with limited data.
method Transformer-based neural network with cross-currency correlation and sentiment analysis.
result Transformer model outperforms other models on some parameters.
New analysis shows transformer models can't learn effectively.
problem Transformer models learning in context can't achieve general predictive accuracy.
method Empirical evidence and mathematical analysis of transformer architecture limitations.
result Transformers cannot achieve general predictive accuracy due to architectural limitations.
Transformers forecast time series in-context, improving efficiency and performance.
problem Overfitting and limited performance in time series forecasting.
method Reformulate time series forecasting as input tokens, aligning with in-context learning mechanisms.
result Consistently better performance across various settings (full-data, few-shot, zero-shot).
Unified transformer-based LT-TTD improves ranking efficiency and quality.
problem Decoupled L1 and L2 models in recommendation and search systems cause irreversible error propagation and suboptimal ranking.
method LT-TTD combines two-tower models with transformer expressivity in a unified listwise learning framework, providing theoretical guarantees and UPQE evaluation.
result LT-TTD reduces irretrievable relevant items and achieves better global optimization than disjoint training.
Sentinel improves time series forecasting by modeling both temporal and channel dependencies.
problem Limited effectiveness of existing transformer-based architectures in multivariate time-series forecasting.
method Proposes Sentinel, a full transformer-based architecture with multi-patch attention mechanism.
result Sentinel achieves better or comparable performance compared to state-of-the-art approaches.
LEMs extend transformer-based architectures for complex execution problems.
problem Handling flexible time boundaries and multiple execution constraints in deep learning.
method Decouples market information processing from execution allocation decisions using TKANs, VSNs, and multi-head attention mechanisms.
result LEMs achieve superior execution performance compared to traditional benchmarks.
Neural dialogue models, despite their successes, still suffer from lack of relevance, diversity, and in many cases coherence in their generated responses. These issues can attributed to reasons including (1) short-range model architectures that capture limited temporal dependencies, (2) limitations of the maximum likel…
Robust Transformer-Based One-Step Stock Index Forecasting via Shifted Data Augmentation
problem Robust stock index forecasting
method Modified Transformer architecture with Shifted Data Augmentation
result Best performance on benchmark datasets
BreakGPT predicts asset price surges using LLMs.
problem Predicting sharp upward movements in volatile financial markets.
method Adapts LLMs for time series forecasting, combining LLM capabilities with Transformer models.
result BreakGPT effectively captures local and global temporal dependencies.
Transformer-based multi-scale model outperforms traditional methods in solving PDEs on irregular domains.
problem Solving partial differential equations on irregular domains using deep learning.
method Introduces Multi-Scale Attention Transformer (\msat{}) for solving PDEs.
result Achieves state-of-the-art generalization on complex geometry problems with significant speedup.
Deep learning models reconstruct volatility surfaces from noisy data under no-arbitrage constraints.
problem Reconstructing implied volatility surfaces from sparse and noisy option quotes.
method Compared multiple neural architectures including Transformers, U-Nets, and variational autoencoders.
result Transformer and U-Net architectures achieve strong reconstruction accuracy, especially under sparse observation regimes.
Efficient algorithm finds fast Transformer models.
problem Slow inference time of Transformer models.
method Decompose Transformer architecture into components, use sampling-based one-shot search.
result Achieved 10% to 30% speedup on pre-trained BERT and 70% on top of a previous state-of-the-art model.
New method improves reliability of depth estimation models.
problem Uncertainty quantification in large-scale vision models.
method Parameter-efficient Bayesian neural networks with PEFT methods.
result Combining PEFT methods with Bayesian inference enhances predictive performance.
Transformer learns long-term dependencies from real-world data.
problem Sample inefficiency in deep reinforcement learning.
method Transformer architecture applied to autoregressive real-world episodes.
result Transformer-based world model generates meaningful experience.
This study evaluates the robustness of transformation-based ensemble defense against evasion attacks.
problem Understanding the reasons behind the robustness improvement in transformation-based ensemble defense.
method Designing two adaptive attacks to evaluate transformation-based ensemble defense, conducting experiments to analyze robustness.
result The robustness improvement is mainly from irreversible transformations rather than the ensemble of models.
TraCeR uses transformers to analyze survival data with longitudinal covariates.
problem Handling longitudinal covariates and assessing model calibration in survival analysis.
method Transformer-based survival analysis framework with factorized self-attention architecture.
result TraCeR achieves significant performance improvements over state-of-the-art methods.
Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context information, has been shown to achieve significantly lower word error rates (WERs) co…
In this paper we investigate continuous speech recognition using electroencephalography (EEG) features using recently introduced end-to-end transformer based automatic speech recognition (ASR) model. Our results demonstrate that transformer based model demonstrate faster training compared to recurrent neural network (R…
Improved model for multivariate time series prediction with simpler architecture.
problem Multivariate probabilistic time series prediction challenges.
method Simplified transformer-based attentional copulas (TACTiS) with linearly scalable parameters.
result Significantly better training dynamics and state-of-the-art performance.
Unified model trained on images and videos using masked autoencoding.
problem Training a single model for multiple visual modalities.
method Masked autoencoding on a Vision Transformer.
result Unified model achieves comparable or better performance than single-modality models.
PolyGen models 3D meshes directly, predicting vertices and faces sequentially.
problem Efficiently modeling 3D geometry for computer graphics, robotics, and games.
method Transformer-based autoregressive model for predicting mesh vertices and faces.
result PolyGen produces high-quality, usable 3D meshes and competitive conditional performance.
We propose the Insertion-Deletion Transformer, a novel transformer-based neural architecture and training method for sequence generation. The model consists of two phases that are executed iteratively, 1) an insertion phase and 2) a deletion phase. The insertion phase parameterizes a distribution of insertions on the c…
Develops a Causal Transformer for estimating counterfactual outcomes from longitudinal data.
problem Estimating counterfactual outcomes over time from observational data is challenging due to complex, long-range dependencies.
method Combines three transformer subnetworks with separate inputs for time-varying covariates, previous treatments, and previous outcomes into a joint network with in-between cross-attentions. Uses a custom, end-to-end training procedure with a counterfactual domain confusion loss to address confounding bias.
result Achieves superior performance over current baselines in synthetic and real-world datasets.
AV-ASR system improves speech recognition with visual context.
problem Improving speech recognition accuracy with visual information.
method Transformer-based architecture with multiresolution and multimodal training.
result Multiresolution training speeds up convergence and improves WER by 18%.
Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows contextual information to be exchanged among sequence elements. While many of the prev…
GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.
problem Lack of explicit geometric information in 3D semantic segmentation models.
method Introduces GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into existing 3D segmentation pipelines.
result Consistent performance gains across multiple benchmarks, including up to +11.5% mIoU on TS40K with PTV3.
FinAI-BERT classifies AI disclosures in financial reports with high accuracy.
problem Systematic detection of AI-related disclosures in financial reports.
method Fine-tuned transformer-based model on a curated dataset.
result Achieved near-perfect classification performance (99.37% accuracy).
A new method uses Transformers for efficient prediction of marked point processes.
problem Efficiently predicting the next event in a sequence given its history.
method Modeling conditional inter-event times with a mixture of log-normals and marks with a Transformer architecture.
result The method achieves state-of-the-art performance and is faster during inference.
Framework detects covert financial market manipulation using LOB representations.
problem Detecting covert financial market manipulation (spoofing) from complex anomaly patterns in multilevel prices.
method Cascaded contrastive representation learning of LOB data.
result Transformer-based architectures achieve state-of-the-art results in detection performance.
Generates high-quality images using sparse DCT representations.
problem Challenges in generating images due to high dimensionality.
method Transformers trained on sparse DCT block sequences.
result Competitive image generation quality with state-of-the-art methods.
Develops methods for training models with few annotations in computer vision tasks.
problem Training models with limited labeled data in computer vision.
method Theoretical, algorithmic, and experimental contributions for Meta-Learning and Semi-Supervised Learning.
result Improves Contrastive Learning and proposes a semi-supervised method for transformer-based object detectors.
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - an…
GenSBI offers JAX-native SBI methods for natural sciences.
problem Lack of native SBI libraries in JAX for natural sciences.
method Flow and diffusion generative models in JAX.
result Near-ideal mean C2ST scores on SBIBM tasks.
We propose the first qualitative hypothesis characterizing the behavior of visual transformation based self-supervision, called the VTSS hypothesis. Given a dataset upon which a self-supervised task is performed while predicting instantiations of a transformation, the hypothesis states that if the predicted instantiati…
Study benchmarks uncertainty quantification in chest X-ray classification.
problem Reliable uncertainty quantification for medical AI models.
method Evaluation of 13 uncertainty quantification methods on MIMIC-CXR-JPG dataset.
result Insights into effectiveness and disentanglement of epistemic and aleatoric uncertainties.
Novel regularization for Vision Transformers improves model generalization and sparsity.
problem Improving generalization and sparsity in Vision Transformers.
method Likelihood-guided variational Ising-based regularization.
result Improved generalization and sparsity in Vision Transformers.
A transformation based on mean curvature is introduced which morphs triangulated surfaces into round spheres.
PatchGT uses non-trainable graph patches to improve graph representation learning.
problem Learning high-level information in graph tasks with direct Transformer models.
method PatchGT segments graphs into non-trainable patches, uses GNN for patch-level learning, and Transformer for graph-level learning.
result PatchGT achieves higher expressiveness and competitive performance on benchmark datasets.
MOCA uses modular attention to estimate causal effects from complex data.
problem Estimating causal effects from observational data with complex, non-linear, and high-dimensional treatment and outcome mechanisms.
method MOCA is a transformer-based framework that separates treatment and outcome modeling through modular design and one-way attention mechanism, with cutting-feedback to prevent outcome influence on treatment representations.
result MOCA outperforms classical estimators and machine learning approaches across various simulated and real-world scenarios.
Informer improves option pricing accuracy in volatile markets.
problem Challenges in accurate option pricing due to market volatility and traditional model limitations.
method Applying Informer, a Transformer-based neural network, for option pricing.
result Informer outperforms traditional models in option pricing accuracy.
Transformer-based method for causal discovery with prior knowledge integration.
problem Complex nonlinear dependencies and spurious correlations in time series data.
method Multi-layer Transformer forecaster with gradient-based causal structure extraction and attention masking for prior knowledge integration.
result Significant improvement in causal discovery and causal lag estimation compared to state-of-the-art methods.
Many common sequential data sources, such as source code and natural language, have a natural tree-structured representation. These trees can be generated by fitting a sequence to a grammar, yielding a hierarchical ordering of the tokens in the sequence. This structure encodes a high degree of syntactic information, ma…
Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model …
Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures. However, insufficient effort has been devoted to the aggregation methods between different convolution graph layers. In this paper, we introduce a graph attribute…
New model recognizes emotions with missing modalities, improving accuracy.
problem Handling missing modalities in emotion recognition.
method Transformer-based architecture with cross-attention and self-attention mechanisms.
result Improvement of 37% in predicting arousal values and 30% in valence values compared to baseline.