Keeping JEPA World Models Plannable When Little of the Frame Moves
cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Latent Goal Prediction from Language for Model-Based Planning
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Policy-Guided World Model Planning for Language-Conditioned Visual Navigation
- ATM: Why Latent World Models Can Fail to Plan
- SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning
- Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
- ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games
- Mastering Diverse Domains through World Models
- Sensorimotor World Models: Perception for Action via Inverse Dynamics
- Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models
- Multistep Inverse Is Not All You Need
- Grounded World Model: Latent Planning with Language Goals
- Predictive but Not Plannable: RC-aux for Latent World Models
- Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning
- Interactive Language: Talking to Robots in Real Time
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