Related papers: Estimating Time Series Foundation Model Transferab…

Tabular data is one of the most ubiquitous sources of information worldwide, spanning a wide variety of domains. This inherent heterogeneity has slowed the development of Tabular Foundation Models (TFMs) capable of fast generalization to…

Deep knowledge tracing models have achieved significant breakthroughs in modeling student learning trajectories. However, these architectures require substantial training time and are prone to overfitting on datasets with short sequences.…

Pre-trained models exhibit strong generalization to various downstream tasks. However, given the numerous models available in the model hub, identifying the most suitable one by individually fine-tuning is time-consuming. In this paper, we…

Recent Tabular Foundation Models (TFMs) have demonstrated state-of-the-art predictive performance, often surpassing Gradient-Boosted Decision Trees (GBDTs). However, the trustworthiness of these models, particularly their uncertainty…

TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerable to label shift, often overfitting…

In practice, it is very demanding and sometimes impossible to collect datasets of tagged data large enough to successfully train a machine learning model, and one possible solution to this problem is transfer learning. This study aims to…

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…

Inspired by recent advances in large language models, foundation models have been developed for zero-shot time series forecasting, enabling prediction on datasets unseen during pretraining. These large-scale models, trained on vast…

Often, constraints arise in deployment settings where even lightweight parameter updates e.g. parameter-efficient fine-tuning could induce model shift or tuning instability. We study test-time adaptation of foundation models for few-shot…

Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require domain-specific feature engineering and substantial labeled data for each task. We introduce…

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…

Recently, there has been a growing interest in time series foundation models that generalize across different downstream tasks. A key to strong foundation models is a diverse pre-training dataset, which is particularly challenging to…

Frontier AI models have achieved remarkable progress, yet recent studies suggest they struggle with compositional reasoning, often performing at or below random chance on established benchmarks. We revisit this problem and show that widely…

Cross-frequency transfer learning (CFTL) has emerged as a popular framework for curating large-scale time series datasets to pre-train foundation forecasting models (FFMs). Although CFTL has shown promise, current benchmarking practices…

Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging. Existing solutions face a trade-off:…

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…

Diffusion models have achieved state-of-the-art performance in generative modeling tasks across various domains. Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific…

Time Series Foundation Models (TSFMs) leverage extensive pretraining to accurately predict unseen time series during inference, without the need for task-specific fine-tuning. Through large-scale evaluations on standard benchmarks, we find…

Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-augmented prediction. However, our empirical analysis reveals a non-trivial limitation of…

The evaluation of time series forecasting models is hindered by a lack of high-quality benchmarks, leading to overestimated assessments of progress. Existing datasets suffer from issues ranging from small-scale, low-frequency, pre-training…