English
Related papers

Related papers: Revisiting the Generic Transformer: Deconstructing…

200 papers

Graph foundation models (GFMs) have recently attracted interest due to the promise of graph neural network (GNN) architectures that generalize zero-shot across graphs of arbitrary scales, feature dimensions, and domains. While existing work…

Machine Learning · Computer Science 2026-03-25 Benjamin Gutteridge , Michael Bronstein , Xiaowen Dong

We propose a unified Transformer-based architecture for wireless signal processing tasks, offering a low-latency, task-adaptive alternative to conventional receiver pipelines. Unlike traditional modular designs, our model integrates channel…

Signal Processing · Electrical Eng. & Systems 2025-09-11 Yuto Kawai , Rajeev Koodli

Recently, time series foundation models have shown promising zero-shot forecasting performance on time series from a wide range of domains. However, it remains unclear whether their success stems from a true understanding of temporal…

Machine Learning · Computer Science 2024-11-12 Willa Potosnak , Cristian Challu , Mononito Goswami , Michał Wiliński , Nina Żukowska , Artur Dubrawski

Template-based program repair research is in need for a common ground to express fix patterns in a standard and reusable manner. We propose to build on the concept of generic patch (also known as semantic patch), which is widely used in the…

Software Engineering · Computer Science 2020-11-30 Anil Koyuncu , Tegawendé F. Bissyandé , Jacques Klein , Yves Le Traon

There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal…

Machine Learning · Computer Science 2025-07-04 Yu-Hsiang Lan , Eric K. Oermann

Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these models remains a significant concern. This problem arises…

Periodicity is a fundamental characteristic of time series data and has long played a central role in forecasting. Recent deep learning methods strengthen the exploitation of periodicity by treating patches as basic tokens, thereby…

Machine Learning · Computer Science 2025-10-07 Yiming Niu , Jinliang Deng , Yongxin Tong

Recent advances in time-series forecasting increasingly rely on pre-trained foundation-style models. While these models often claim broad generalization, existing evaluation protocols provide limited evidence. Indeed, most current…

Deep learning models have grown increasingly popular in time series applications. However, the large quantity of newly proposed architectures, together with often contradictory empirical results, makes it difficult to assess which…

Machine Learning · Computer Science 2025-12-30 Valentina Moretti , Andrea Cini , Ivan Marisca , Cesare Alippi

Transformers have achieved remarkable success in time series modeling, yet their internal mechanisms remain opaque. This work demystifies the Transformer encoder by establishing its fundamental equivalence to a Graph Convolutional Network…

Machine Learning · Computer Science 2025-10-21 Chen Zhang , Weixin Bu , Wendong Xu , Runsheng Yu , Yik-Chung Wu , Ngai Wong

Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets? This work provides positive evidence to this using a broad…

Machine Learning · Computer Science 2020-12-16 Boris N. Oreshkin , Dmitri Carpov , Nicolas Chapados , Yoshua Bengio

Deep learning utilizing transformers has recently achieved a lot of success in many vital areas such as natural language processing, computer vision, anomaly detection, and recommendation systems, among many others. Among several merits of…

Machine Learning · Computer Science 2023-12-05 Lena Sasal , Tanujit Chakraborty , Abdenour Hadid

Modern Foundation Models (FMs) are typically trained on corpora spanning a wide range of different data modalities, topics and downstream tasks. Utilizing these models can be very computationally expensive and is out of reach for most…

Machine Learning · Computer Science 2025-06-09 Andrey Zhmoginov , Jihwan Lee , Mark Sandler

Time-Series Foundation Models (TSFMs) are rapidly transitioning from research prototypes to core components of critical decision-making systems, driven by their impressive zero-shot forecasting capabilities. However, as their deployment…

Machine Learning · Computer Science 2025-12-09 Jiawen Zhang , Zhenwei Zhang , Shun Zheng , Xumeng Wen , Jia Li , Jiang Bian

Transformers for time series forecasting mainly model time series from limited or fixed scales, making it challenging to capture different characteristics spanning various scales. We propose Pathformer, a multi-scale Transformer with…

Machine Learning · Computer Science 2024-09-17 Peng Chen , Yingying Zhang , Yunyao Cheng , Yang Shu , Yihang Wang , Qingsong Wen , Bin Yang , Chenjuan Guo

Foundation Models are designed to serve as versatile embedding machines, with strong zero shot capabilities and superior generalization performance when fine-tuned on diverse downstream tasks. While this is largely true for language and…

Machine Learning · Computer Science 2025-10-08 Nouha Karaouli , Denis Coquenet , Elisa Fromont , Martial Mermillod , Marina Reyboz

Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training, yet fine-tuning remains critical for boosting performance in domains with limited public data. With the growing number of TSFMs,…

Machine Learning · Computer Science 2025-09-30 Qingren Yao , Ming Jin , Chengqi Zhang , Chao-Han Huck Yang , Jun Qi , Shirui Pan

The extensive adoption of web technologies in the finance and investment sectors has led to an explosion of financial data, which contributes to the complexity of the forecasting task. Traditional machine learning models exhibit limitations…

Machine Learning · Computer Science 2026-01-21 Renjun Jia , Zian Liu , Peng Zhu , Dawei Cheng , Yuqi Liang

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Zhendong Wang , Yifan Jiang , Huangjie Zheng , Peihao Wang , Pengcheng He , Zhangyang Wang , Weizhu Chen , Mingyuan Zhou

Transformers have recently emerged as powerful neural networks for graph learning, showcasing state-of-the-art performance on several graph property prediction tasks. However, these results have been limited to small-scale graphs, where the…

Machine Learning · Computer Science 2023-12-19 Vijay Prakash Dwivedi , Yozen Liu , Anh Tuan Luu , Xavier Bresson , Neil Shah , Tong Zhao