VF
Vasilii Feofanov
cs.LGcs.AIstat.MLcs.CV
On Valency
published · living versionsW_5gxuhfxj·v1 · currentpublished
Turning TS2Vec into a Foundation Model for Time Series Classification
with Zhenghan Tai, Andrei Ermakov, Irina Rish
1 version
Preprints & journals
21 papers in the corpus · 2019–2026Turning TS2Vec into a Foundation Model for Time Series Classification2610.28602v1 · Vasilii Feofanov, Zhenghan Tai, Andrei Ermakov et al.2026 · 0 citationsarXivon Valency
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series2605.20449v1 · Alexis Roger, Prateek Humane, Zhenghan Tai et al.2026 · 0 citationsarXiv
Layer by layer, module by module: Choose both for optimal OOD probing of ViT2603.05280v1 · Ambroise Odonnat, Vasilii Feofanov, Laetitia Chapel et al.2026 · 0 citationsarXiv
UTICA: Multi-Objective Self-Distllation Foundation Model Pretraining for Time Series Classification2603.01348v1 · Yessin Moakher, Youssef Attia El Hili, Vasilii Feofanov2026 · 0 citationsarXiv
MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies2602.17868v1 · Vasilii Feofanov, Songkang Wen, Jianfeng Zhang et al.2026 · 0 citationsarXiv
Leveraging Generic Time Series Foundation Models for EEG Classification2510.27522v1 · Th'eo Gnassounou, Yessin Moakher, Shifeng Xie et al.2025 · 0 citationsNeurIPS 2025 Workshop "Recent Advances in Time Series Foundation Models Have We Reached the 'BERT Moment'?"
CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data2508.02879v3 · Shifeng Xie, Vasilii Feofanov, Ambroise Odonnat et al.2025 · 0 citationsICLR 2026 Oral
Unlocking Pretrained Vision Transformers for Time Series Classification2506.08641v3 · Simon Roschmann, Quentin Bouniot, Vasilii Feofanov et al.2025 · 0 citationsarXiv
Mantis: Lightweight Foundation Model for Time Series Classification2502.15637v2 · Vasilii Feofanov, Songkang Wen, Shifeng Xie et al.2025 · 1 citationProceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026
AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting2502.10235v1 · Abdelhakim Benechehab, Vasilii Feofanov, Giuseppe Paolo et al.2025 · 0 citationsarXiv
Measuring Pre-training Data Quality without Labels for Time Series Foundation Models2412.06368v1 · Songkang Wen, Vasilii Feofanov, Jianfeng Zhang2024 · 0 citationsNeurIPS 2024 Workshop on Time Series in the Age of Large Models
User-friendly Foundation Model Adapters for Multivariate Time Series Classification2409.12264v1 · Vasilii Feofanov, Romain Ilbert, Malik Tiomoko et al.2024 · 0 citationsarXiv
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting2406.10327v1 · Romain Ilbert, Malik Tiomoko, Cosme Louart et al.2024 · 3 citationsarXiv
MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts2405.18979v3 · Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov et al.2024 · 2 citationsarXiv
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention2402.10198v3 · Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov et al.2024 · 1 citationarXiv
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift2401.08909v3 · Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov et al.2024 · 0 citationsarXiv
Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias2310.14814v4 · Ambroise Odonnat, Vasilii Feofanov, Ievgen Redko2023 · 3 citationsarXiv
Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption2310.13434v1 · Vasilii Feofanov, Malik Tiomoko, Aladin Virmaux2023 · 2 citationsProceedings of the 40th International Conference on Machine Learning, PMLR 202:10008-10033, 2023
Self-Training: A Survey2202.12040v6 · Massih-Reza Amini, Vasilii Feofanov, Loic Pauletto et al.2022 · 156 citationsarXiv
Multi-class Probabilistic Bounds for Self-learning2109.14422v1 · Vasilii Feofanov, Emilie Devijver, Massih-Reza Amini2021 · 0 citationsarXiv
Semi-supervised Wrapper Feature Selection by Modeling Imperfect Labels1911.04841v2 · Vasilii Feofanov, Emilie Devijver, Massih-Reza Amini2019 · 1 citationarXiv
Career total: 27 works. 21 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.