Related papers: ViTime: Foundation Model for Time Series Forecasti…
Forecasting from partial observations is central to world modeling. Many recent methods represent the world through images, and reduce forecasting to stochastic video generation. Although such methods excel at realism and visual fidelity,…
Time series foundation models (TSFMs) such as Lag-Llama, TimeGPT, Chronos, MOMENT, UniTS, and TimesFM have shown strong generalization and zero-shot capabilities for time series forecasting, anomaly detection, classification, and…
Time series foundation models (TSFMs) promise to be powerful tools for a wide range of applications. However, their internal representations and learned concepts are still not well understood. In this study, we investigate the structure and…
Time series forecasting is a subject of significant scientific and industrial importance. Despite the widespread utilization of forecasting methods, there is a dearth of research aimed at comprehending the conditions under which these…
Vision foundation models (VFMs) have demonstrated remarkable performance across a wide range of downstream tasks. While several VFM adapters have shown promising results by leveraging the prior knowledge of VFMs, we identify two…
Deep learning has shown strong performance in time series forecasting tasks. However, issues such as missing values and anomalies in sequential data hinder its further development in prediction tasks. Previous research has primarily focused…
We investigate the effectiveness of time series foundation models (TSFMs) for crowd flow prediction, focusing on Moirai and TimesFM. Evaluated on three real-world mobility datasets-Bike NYC, Taxi Beijing, and Spanish national OD flows-these…
Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…
Multivariate Time Series Forecasting (MTSF) has long been a key research focus. Traditionally, these studies assume a fixed number of variables, but in real-world applications, Cyber-Physical Systems often expand as new sensors are…
Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot…
Long-term time series forecasting (LTSF) is a critical task across diverse domains. Despite significant advancements in LTSF research, we identify a performance bottleneck in existing LTSF methods caused by the inadequate modeling of…
Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding. However, most methods rely on training…
In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two…
The prevailing Direct Forecasting (DF) paradigm dominates Long-term Time Series Forecasting (LTSF) by forcing models to predict the entire future horizon in a single forward pass. While efficient, this rigid coupling of output and…
Time series modeling and forecasting has fundamental importance to various practical domains. Thus a lot of active research works is going on in this subject during several years. Many important models have been proposed in literature for…
Using a time series model to mimic an observed time series has a long history. However, with regard to this objective, conventional estimation methods for discrete-time dynamical models are frequently found to be wanting. In fact, they are…
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…
Satellite image time series (SITS) provide continuous observations of the Earth's surface, making them essential for applications such as environmental management and disaster assessment. However, existing spatiotemporal foundation models…
We introduce VidTFS, a Training-free, open-vocabulary video goal and action inference framework that combines the frozen vision foundational model (VFM) and large language model (LLM) with a novel dynamic Frame Selection module. Our…
Time Series Foundation Models (TSFMs) represent a new paradigm for time-series forecasting, promising zero-shot predictions without the need for task-specific training or fine-tuning. However, similar to Large Language Models (LLMs), the…