PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Revisiting Feature Prediction for Learning Visual Representations from Video
- CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations
- Message Passing Neural PDE Solvers
- CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations
- Parameterized Physics-informed Neural Networks for Parameterized PDEs
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling
- Learning Physical Operators using Neural Operators
- Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
- Predicting Physics in Mesh-reduced Space with Temporal Attention
- DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
- When Does LeJEPA Learn a World Model?
- Generalized Neural Operator for Parametric and Boundary-Value Problems
- Fourier Neural Operator for Parametric Partial Differential Equations
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
- V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
- Representation Learning for Spatiotemporal Physical Systems
- Zebra: In-Context Generative Pretraining for Solving Parametric PDEs
- Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems