Related papers: Rapid Augmentations for Time Series (RATS): A High…
Data augmentation is widely used for machine learning; however, an effective method to apply data augmentation has not been established even though it includes several factors that should be tuned carefully. One such factor is sample…
Deep learning has performed remarkably well on many tasks recently. However, the superior performance of deep models relies heavily on the availability of a large number of training data, which limits the wide adaptation of deep models on…
Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are often small. In order to…
Data augmentation is a crucial technique for improving model generalization and robustness, particularly in deep learning models where training data is limited. Although many augmentation methods have been developed for time series…
Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…
Time series observations can be seen as realizations of an underlying dynamical system governed by rules that we typically do not know. For time series learning tasks, we need to understand that we fit our model on available data, which is…
Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series…
Neural Radiance Fields (NeRF)-based models have achieved remarkable success in 3D reconstruction and rendering tasks. However, during both training and inference, these models rely heavily on dense point sampling along rays from multiple…
We introduce ALT, an open-source Python package created for efficient and accurate time series classification (TSC). The package implements the adaptive law-based transformation (ALT) algorithm, which transforms raw time series data into a…
Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating…
Retrieval-augmented generation (RAG) has achieved significant success in information retrieval to assist large language models LLMs because it builds an external knowledge database. However, it also has many problems, it consumes a lot of…
Time-series anomaly detection (TSAD) is a critical component in monitoring complex systems, yet modern deep learning-based detectors are often highly sensitive to localized input corruptions and structured noise. We propose ARTA…
RAG (Retrieval Augmented Generation) allows LLMs (large language models) to generate better responses with external knowledge, but using more external knowledge often improves generation quality at the expense of response delay. Prior work…
The rapid increase in the number of parameters in large language models (LLMs) has significantly increased the cost involved in fine-tuning and retraining LLMs, a necessity for keeping models up to date and improving accuracy.…
This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…
RAG systems face limitations when semantic relevance alone does not guarantee improved generation quality. This issue becomes particularly evident due to the sensitivity of large language models (LLMs) to the ordering of few-shot prompts,…
Time Series Analysis (TSA) is a critical workload to extract valuable information from collections of sequential data, e.g., detecting anomalies in electrocardiograms. Subsequence Dynamic Time Warping (sDTW) is the state-of-the-art…
Automatic lyrics transcription (ALT), which can be regarded as automatic speech recognition (ASR) on singing voice, is an interesting and practical topic in academia and industry. ALT has not been well developed mainly due to the dearth of…
While current time series research focuses on developing new models, crucial questions of selecting an optimal approach for training such models are underexplored. Tsururu, a Python library introduced in this paper, bridges SoTA research…
Retrieval-augmented generation (RAG), which combines large language models (LLMs) with retrievals from external knowledge databases, is emerging as a popular approach for reliable LLM serving. However, efficient RAG serving remains an open…