Cover Image

LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Roger, Alexis, Humane, Prateek, Tai, Zhenghan, Legate, Gwen, Mircea, Andrei, Feofanov, Vasilii, Rish, Irina
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models
by: Roger, Alexis, et al.
Published: (2025)

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
by: Legate, Gwen, et al.
Published: (2025)

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting
by: Riachi, Roland, et al.
Published: (2025)

UTICA: Multi-Objective Self-Distllation Foundation Model Pretraining for Time Series Classification
by: Moakher, Yessin, et al.
Published: (2026)

Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
by: Roschmann, Simon, et al.
Published: (2025)

Influence Functions for Efficient Data Selection in Reasoning
by: Humane, Prateek, et al.
Published: (2025)

Measuring Pre-training Data Quality without Labels for Time Series Foundation Models
by: Wen, Songkang, et al.
Published: (2024)

Towards ethical multimodal systems
by: Roger, Alexis, et al.
Published: (2023)

Leveraging Generic Time Series Foundation Models for EEG Classification
by: Gnassounou, Théo, et al.
Published: (2025)

CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language Models
by: Roger, Alexis, et al.
Published: (2025)

User-friendly Foundation Model Adapters for Multivariate Time Series Classification
by: Feofanov, Vasilii, et al.
Published: (2024)

MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies
by: Feofanov, Vasilii, et al.
Published: (2026)

CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data
by: Xie, Shifeng, et al.
Published: (2025)

Image Tiling for High-Resolution Reasoning: Balancing Local Detail with Global Context
by: de Margerie, Anatole Jacquin, et al.
Published: (2025)

AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
by: Benechehab, Abdelhakim, et al.
Published: (2025)

Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
by: Odonnat, Ambroise, et al.
Published: (2023)

Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
by: Ilbert, Romain, et al.
Published: (2024)

SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
by: Ilbert, Romain, et al.
Published: (2024)

Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning
by: Mircea, Andrei, et al.
Published: (2025)

Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
by: Bhagwatkar, Rishika, et al.
Published: (2024)

Mantis: Lightweight Calibrated Foundation Model for User-Friendly Time Series Classification
by: Feofanov, Vasilii, et al.
Published: (2025)

Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
by: Kaushal, Ayush, et al.
Published: (2024)

Layer by layer, module by module: Choose both for optimal OOD probing of ViT
by: Odonnat, Ambroise, et al.
Published: (2026)

On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series
by: Dey, Sharmita, et al.
Published: (2026)

Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning
by: Darvishi-Bayazi, Mohammad-Javad, et al.
Published: (2023)

MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
by: Xie, Renchunzi, et al.
Published: (2024)

Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
by: Xie, Renchunzi, et al.
Published: (2024)

CC-Time: Cross-Model and Cross-Modality Time Series Forecasting
by: Chen, Peng, et al.
Published: (2025)

Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
by: Liu, Chenxi, et al.
Published: (2025)

TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
by: Liu, Chenxi, et al.
Published: (2024)

Self-Training: A Survey
by: Amini, Massih-Reza, et al.
Published: (2022)

Stationarity of Manifold Time Series
by: Zhu, Junhao, et al.
Published: (2024)

STEP: Scientific Time-Series Encoder Pretraining via Cross-Domain Distillation
by: Zhang, Chen, et al.
Published: (2026)

Knowledge Distillation for Federated Learning: a Practical Guide
by: Mora, Alessio, et al.
Published: (2022)

On the Adversarial Robustness of Discrete Image Tokenizers
by: Bhagwatkar, Rishika, et al.
Published: (2026)

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
by: Riemer, Matthew, et al.
Published: (2024)

Handling Delay in Real-Time Reinforcement Learning
by: Anokhin, Ivan, et al.
Published: (2025)

FiCoTS: Fine-to-Coarse LLM-Enhanced Hierarchical Cross-Modality Interaction for Time Series Forecasting
by: Lyu, Yafei, et al.
Published: (2025)

Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection
by: Yu, Cai, et al.
Published: (2024)

LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions
by: Liu, Chenxi, et al.
Published: (2025)