BeliefGraph-JEPA: Structured Latent World Models for Action-Conditioned Time Series

arXiv:2610.05409 · cs.LG, cs.AI · Submitted 2026-10-04 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-04

Updated: 2026-10-04

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Latent World Models — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Chronos-2: From Univariate to Universal Forecasting
• DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
• DRIFT: Direct-Recursive Intervention-Conditioned Forecasting of ICU Physiological Trajectories
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Joint Embeddings Go Temporal
• Wastewater Treatment Plant Data for Nutrient Removal System
• Long-term Forecasting with TiDE: Time-series Dense Encoder
• Chronos: Learning the Language of Time Series
• A decoder-only foundation model for time-series forecasting
• ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
• Efficiently Modeling Long Sequences with Structured State Spaces
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Revisiting Feature Prediction for Learning Visual Representations from Video
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
• Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting
• Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding
• TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling
• EHRWorld: A Patient-Centric Medical World Model for Long-Horizon Clinical Trajectories

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