Related papers: Exploring Fine-Tuning for Tabular Foundation Model…

Parameter-Efficient Fine-Tuning (PEFT) methods achieve performance comparable to Full Fine-Tuning (FFT) while requiring significantly fewer computing resources, making it the go-to choice for researchers. We find that although PEFT can…

Point cloud foundation models demonstrate strong generalization, yet adapting them to downstream tasks remains challenging in low-data regimes. Full fine-tuning often leads to overfitting and significant drift from pre-trained…

Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. However, new approaches to FL often discuss their contributions involving small deep-learning…

Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets by meta-learning over synthetic data-generating processes -- making them highly attractive for practitioners who cannot afford large…

This survey delves into the realm of Parameter-Efficient Fine-Tuning (PEFT) within the context of Foundation Models (FMs). PEFT, a cost-effective fine-tuning technique, minimizes parameters and computational complexity while striving for…

Foundation models have revolutionized artificial intelligence by providing robust, versatile architectures pre-trained on large-scale datasets. However, adapting these massive models to specific downstream tasks requires fine-tuning, which…

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage…

Parameter-efficient fine-tuning (PEFT) has attracted significant attention due to the growth of pre-trained model sizes and the need to fine-tune (FT) them for superior downstream performance. Despite a surge in new PEFT methods, a…

Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting. However, an important yet underexplored challenge is how to effectively finetune TSFMs on specific downstream tasks. While naive…

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…

Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part of the input. ICL incurs substantial…

Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of large-scale pretraining to tabular domains. However, their adoption remains limited due to heterogeneous preprocessing pipelines,…

The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic…

Foundation models are an emerging research direction in tabular deep learning. Notably, TabPFNv2 recently claimed superior performance over traditional GBDT-based methods on small-scale datasets using an in-context learning paradigm, which…

Accurate molecular property prediction is central to drug discovery, catalysis, and process design, yet real-world applications are often limited by small datasets. Molecular foundation models provide a promising direction by learning…

The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks. Traditional…

Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale of LMMs continues…

Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data-scarce domains. For such few-shot scenarios, specialized methods like TabPFN - a…

Graph foundation models (GFMs) have recently emerged as a promising paradigm for achieving broad generalization across various graph data. However, existing GFMs are often trained on datasets that may not fully reflect real-world graphs,…

Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference time. Adapting a…