Related papers: SeqFusion: Sequential Fusion of Pre-Trained Models…

Accurate forecasting in financial markets requires integrating diverse data sources, from historical prices to macroeconomic indicators and financial news. However, existing models often fail to align these modalities effectively, limiting…

We introduce LatentTimePFN (LaT-PFN), a foundational Time Series model with a strong embedding space that enables zero-shot forecasting. To achieve this, we perform in-context learning in latent space utilizing a novel integration of the…

This paper proposes Stochastic Geographic Gradient Fusion (SGFusion), a novel training algorithm to leverage the geographic information of mobile users in Federated Learning (FL). SGFusion maps the data collected by mobile devices onto…

Conventional deep models have achieved unprecedented success in time series forecasting. However, facing the challenge of cross-domain generalization, existing studies utilize statistical prior as prompt engineering fails under the huge…

Predictive modeling and time-pattern analysis are increasingly critical in this swiftly shifting retail environment to improve operational efficiency and informed decision-making. This paper reports a comprehensive application of…

Diffusion Models have demonstrated remarkable capabilities in handling inverse problems, offering high-quality posterior-sampling-based solutions. Despite significant advances, a fundamental trade-off persists regarding the way the…

Most prognostic methods require a decent amount of data for model training. In reality, however, the amount of historical data owned by a single organization might be small or not large enough to train a reliable prognostic model. To…

As an enabler technique, data fusion has gained great attention in the context of Internet of things (IoT). In traditional settings, data fusion is done at the cloud server. So the data to be fused should be transferred from the sensor…

Tabular foundation models, particularly Prior-data Fitted Networks like TabPFN have emerged as the leading contender in a myriad of tasks ranging from data imputation to label prediction on the tabular data format surpassing the historical…

The diversity of time series applications and scarcity of domain-specific data highlight the need for time-series models with strong few-shot learning capabilities. In this work, we propose a novel training scheme and a transformer-based…

The zero-shot capabilities of foundation models (FMs) for time series forecasting offer promising potentials in conformal prediction, as most of the available data can be allocated to calibration. This study compares the performance of Time…

In recent years, generative pre-trained paradigms such as Large Language Models (LLMs) and Large Vision Models (LVMs) have achieved revolutionary advancements and widespread real-world applications. Particularly, the emergence of…

Scaling laws motivate the development of Time Series Foundation Models (TSFMs) that pre-train vast parameters and achieve remarkable zero-shot forecasting performance. Surprisingly, even after fine-tuning, TSFMs cannot consistently…

Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient…

Existing deep learning methods for remote sensing image fusion often suffer from poor generalization when applied to unseen datasets due to the limited availability of real training data and the domain gap between different satellite…

Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential…

Many prediction problems across science and engineering, especially in finance and economics, involve large cross-sections of individual time series, where each unit (e.g., a loan, stock, or customer) is driven by unit-level features and…

The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural…

Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine learning methods. We find that zero-shot TFMs already achieve…

We propose a task-agnostic framework for multimodal fusion of time series and single timestamp images, enabling cross-modal generation and robust downstream performance. Our approach explores deterministic and learned strategies for time…