Pythia: Toward Foundation World Models for Multimodal Time Series

arXiv:2610.05240 · cs.LG, cs.AI · Submitted 2026-10-04 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-04

Updated: 2026-10-04

Terminology

• World Model — 1× in this paper · explained in 7 episodes

Sources

• Chronos-2: From Univariate to Universal Forecasting
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context
• Position: Universal Time Series Foundation Models Rest on a Category Error
• Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models
• Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
• Joint Embeddings Go Temporal
• TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models
• Toto 2.0: Time Series Forecasting Enters the Scaling Era
• TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• Moirai 2.0: When Less Is More for Time Series Forecasting
• Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
• Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
• Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics
• Does Text Actually Help? Uncovering and Resolving Text Collapse in Multimodal Time Series Forecasting
• Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting
• LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting
• Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks