Related papers: A Comparative Study on How Data Normalization Affe…

Time series foundation models (TSFMs) require diverse, real-world datasets to adapt across varying domains and temporal frequencies. However, current large-scale datasets predominantly focus on low-frequency time series with sampling…

Visual-language foundation Models (FMs) exhibit remarkable zero-shot generalization across diverse tasks, largely attributed to extensive pre-training on largescale datasets. However, their robustness on low-resolution/pixelated (LR)…

Time series foundation models have demonstrated strong performance in zero-shot learning, making them well-suited for predicting rapidly evolving patterns in real-world applications where relevant training data are scarce. However, most of…

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to inherited biases that can impact their…

Foundation models (FMs) have revolutionized computer vision, enabling effective learning across different domains. However, their performance under domain shift is yet underexplored. This paper investigates the zero-shot domain adaptation…

Time series foundation models excel in zero-shot forecasting, handling diverse tasks without explicit training. However, the advancement of these models has been hindered by the lack of comprehensive benchmarks. To address this gap, we…

Behavioral Foundation Models (BFMs) proved successful in producing policies for arbitrary tasks in a zero-shot manner, requiring no test-time training or task-specific fine-tuning. Among the most promising BFMs are the ones that estimate…

Time series forecasting (TSF) possesses great practical values in various fields, including power and energy, transportation, etc. TSF methods have been studied based on knowledge from classical statistics to modern deep learning. Yet, all…

Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…

Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and…

Data-driven health monitoring of power converters remains limited by poor generalization to unseen operating conditions. This work addresses this out-of-distribution (OOD) challenge by building a domain-specific time-series foundation model…

The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic…

Time Series Foundation Models (TSFMs) have shown significant impact through their model capacity, scalability, and zero-shot generalization. However, due to the heterogeneity of inter-variate dependencies and the backbone scalability on…

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only approaches underperforming on challenging benchmarks. This paper presents…

Accurate forecasting of sequential data streams is a cornerstone of modern Web services, supporting applications such as traffic management, user behavior modeling, and online anomaly prevention. However, in many Web environments, new…

While large language models have rapidly evolved towards general artificial intelligence, their versatility in analyzing time series data remains limited. To address this limitation, we propose a novel normalization technique that considers…

Thanks to the recent developments of Convolutional Neural Networks, the performance of face verification methods has increased rapidly. In a typical face verification method, feature normalization is a critical step for boosting…

Due to the scarcity of annotated data and the substantial computational costs of model, conventional tuning methods in medical image segmentation face critical challenges. Current approaches to adapting pretrained models, including…

Astronomical time-series analysis faces a critical limitation: the scarcity of labeled observational data. We present a pre-training approach that leverages simulations, significantly reducing the need for labeled examples from real…