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

Recent time series modeling faces a sharp divide between numerical generation and semantic understanding, with research showing that generation models often rely on superficial pattern matching, while understanding-oriented models struggle…

Time series foundation models excel at diverse time series forecasting tasks, but their capacity for continuous improvement through incremental learning remains unexplored. We present the first comprehensive study investigating these…

We propose ContextLM, a framework that implicitly learns multi-token prediction by augmenting standard pretraining with an intrinsic next-context prediction objective. ContextLM builds a language model on top of context embeddings that span…

In-context Learning enables training-free adaptation via demonstrations but remains highly sensitive to example selection and formatting. In unified multimodal models spanning understanding and generation, this sensitivity is exacerbated by…

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored.…

Transformer-based language models excel at in-context learning (ICL), where they can adapt to new tasks based on contextual examples, without parameter updates. In a specific form of ICL, which we refer to as \textit{contextual recall},…

Foundational Models are an emerging widely used technique of GenAI. These models are distinguished by their scalability and the ease with which they can be adapted through the exploitation of Transfer Learning. The availability of high…

Astronomical surveys produce time-series data by observing stellar objects across multiple wavelength bands. Foundational transformer-based models, such as Astromer, encode each time-series as a sequence of embeddings of uniform dimensions.…

Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data. Most of the state-of-the-art architectures exploit either temporal or inter-channel dependencies,…

Traditional time series analysis has long relied on pattern recognition, trained on static and well-established benchmarks. However, in real-world settings -- where policies shift, human behavior adapts, and unexpected events unfold --…

With the rising global burden of chronic diseases and the multimodal and heterogeneous clinical data (medical imaging, free-text recordings, wearable sensor streams, etc.), there is an urgent need for a unified multimodal AI framework that…

Effective analysis of time series data presents significant challenges due to the complex temporal dependencies and cross-channel interactions in multivariate data. Inspired by the way human analysts visually inspect time series to uncover…

Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic,…

A foundation model like GPT elicits many emergent abilities, owing to the pre-training with broad inclusion of data and the use of the powerful Transformer architecture. While foundation models in natural languages are prevalent, can we…

Reconstructing precise clinical timelines is essential for modeling patient trajectories and forecasting risk in complex, heterogeneous conditions like sepsis. While unstructured clinical narratives offer semantically rich and contextually…

Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment, including zero-shot classification and cross-modal retrieval. However, existing models typically rely on millions of paired…

Time series data is fundamental to decision-making across many domains including healthcare, finance, power systems, and logistics. However, analyzing this data correctly often requires incorporating unstructured contextual information,…

Advancements in self-supervised pre-training (SSL) have significantly advanced the field of learning transferable time series representations, which can be very useful in enhancing the downstream task. Despite being effective, most existing…

Guiding users through complex procedural plans is an inherently multimodal task in which having visually illustrated plan steps is crucial to deliver an effective plan guidance. However, existing works on plan-following language models…

Time series modeling holds significant importance in many real-world applications and has been extensively studied. While pre-trained foundation models have made impressive strides in the fields of natural language processing (NLP) and…