Related papers: Chronicle: A Multimodal Foundation Model for Joint…

In-context learning (ICL) enables task adaptation at inference time by conditioning on demonstrations rather than updating model parameters. Although recent time-series foundation models incorporate contextual conditioning, retrieval, or…

The ubiquity of time series data creates a strong demand for general-purpose foundation models, yet developing them for classification remains a significant challenge, largely due to the high cost of labeled data. Foundation models capable…

Time series analysis is crucial in fields like finance, transportation, and industry. However, traditional models often focus solely on temporal features, limiting their ability to capture underlying information. This paper proposes a novel…

Multimodal foundation models aim to create a unified representation space that abstracts away from surface features like language syntax or modality differences. To investigate this, we study the internal representations of three recent…

Most existing single-modal time series models rely solely on numerical series, which suffer from the limitations imposed by insufficient information. Recent studies have revealed that multimodal models can address the core issue by…

This paper presents M3L-Contrast -- a novel multimodal multilingual (M3L) neural topic model for comparable data that maps texts from multiple languages and images into a shared topic space. Our model is trained jointly on texts and images…

Time series foundation models have shown impressive performance on a variety of tasks, across a wide range of domains, even in zero-shot settings. However, most of these models are designed to handle short univariate time series as an…

Recently, there has been growing interest in incorporating textual information into foundation models for time series forecasting. However, it remains unclear whether and under what conditions such multimodal integration consistently yields…

Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and take enormous amounts of compute to train. We make use of this resource, together with the observation that LLMs are able to transfer knowledge and…

Large language models (LLMs) show promise for health applications when combined with behavioral sensing data. Traditional approaches convert sensor data into text prompts, but this process is prone to errors, computationally expensive, and…

Large Language Models (LLMs) have emerged as a promising paradigm for time series analytics, leveraging their massive parameters and the shared sequential nature of textual and time series data. However, a cross-modality gap exists between…

Recently, large language models (LLMs) have demonstrated powerful capabilities in performing various tasks and thus are applied by recent studies to time series forecasting (TSF) tasks, which predict future values with the given historical…

We present Chameleon, a family of early-fusion token-based mixed-modal models capable of understanding and generating images and text in any arbitrary sequence. We outline a stable training approach from inception, an alignment recipe, and…

While existing time series foundation models primarily rely on large-scale unimodal pretraining, they lack complementary modalities to enhance time series understanding. Building multimodal foundation models is a natural next step, but it…

Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining preconditions time series training with a reusable manifold. A…

Expanding multimodal representations to novel modalities is constrained by reliance on large-scale paired datasets (e.g., text-image, text-audio, text-3D, text-molecule), which are costly and often infeasible in domains requiring expert…

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based…

The present study explores the interpretability of latent spaces produced by time series foundation models, focusing on their potential for visual analysis tasks. Specifically, we evaluate the MOMENT family of models, a set of…

Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small)…

While multimodal foundation models can now natively work with data beyond text, they remain underutilized in analyzing the considerable amounts of multi-dimensional time-series data in fields like healthcare, finance, and social sciences,…