# Causal-JEPA: Learning World Models through Object-Level Latent Masking

arXiv: https://arxiv.org/abs/2602.11389 · HTML: https://mlsanity.com/paper/2602.11389/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 40 of its 54 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 30 of 40)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [PHYRE: A New Benchmark for Physical Reasoning](https://mlsanity.com/paper/1908.05656/) (2019)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities](https://mlsanity.com/paper/2306.04829/) (2023)
- [Causal Influence Detection for Improving Efficiency in Reinforcement Learning](https://mlsanity.com/paper/2106.03443/) (2021)
- [Attention over learned object embeddings enables complex visual reasoning](https://mlsanity.com/paper/2012.08508/) (2020)
- [Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning](https://mlsanity.com/paper/2107.00848/) (2021)
- [Self-supervised Object-Centric Learning for Videos](https://mlsanity.com/paper/2310.06907/) (2023)
- [Motion-Guided Masking for Spatiotemporal Representation Learning](https://mlsanity.com/paper/2308.12962/) (2023)
- [Generative Video Transformer: Can Objects be the Words?](https://mlsanity.com/paper/2107.09240/) (2021)
- [SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels](https://mlsanity.com/paper/2410.08822/) (2024)
- [Masked Images Are Counterfactual Samples for Robust Fine-tuning](https://mlsanity.com/paper/2303.03052/) (2023)
- [Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions](https://mlsanity.com/paper/2302.11850/) (2023)

## Built on by (most cited first, 29 of 29)

- [Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control](https://mlsanity.com/paper/2607.25337/) (2026)
- [INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models](https://mlsanity.com/paper/2607.26056/) (2026)
- [A Generalization Theory for JEPA-Based World Models](https://mlsanity.com/paper/2606.27014/) (2026)
- [Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations](https://mlsanity.com/paper/2605.14937/) (2026)
- [Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging](https://mlsanity.com/paper/2606.14957/) (2026)
- [Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control](https://mlsanity.com/paper/2607.04978/) (2026)
- [From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery](https://mlsanity.com/paper/2607.12474/) (2026)
- [Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics](https://mlsanity.com/paper/2605.15465/) (2026)
- [ProWorld: Progress-Aware Hyperbolic World Models for Long-Horizon Visual Goal Reaching](https://mlsanity.com/paper/2608.01926/) (2026)
- [Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks](https://mlsanity.com/paper/2606.08775/) (2026)
- [MultiEcho: An Experimental Science of Learned Worlds](https://mlsanity.com/paper/2609.33347/) (2026)
- [One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA](https://mlsanity.com/paper/2606.10572/) (2026)
- [Einstein World Models](https://mlsanity.com/paper/2606.26969/) (2026)
- [Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix](https://mlsanity.com/paper/2607.06925/) (2026)
- [Learning Implicit Causal World Models from Multi-Agent Demonstrations](https://mlsanity.com/paper/2607.26336/) (2026)
- [SR-JEPA: Learning Predictive Latent State in 3D Scenes](https://mlsanity.com/paper/2608.05774/) (2026)
- [Toward a Causal Data Management Ecosystem for Decision Making and Agentic AI](https://mlsanity.com/paper/2608.07214/) (2026)
- [Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models](https://mlsanity.com/paper/2608.12078/) (2026)
- [Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models](https://mlsanity.com/paper/2609.19674/) (2026)
- [Representation World Model: Learning States, Transition and Executable Plans in Representation](https://mlsanity.com/paper/2609.29171/) (2026)
- [Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage](https://mlsanity.com/paper/2609.30214/) (2026)
- [I Act Therefore I Am: When Is JEPA's Action-Conditioning Enough to Learn Causal Mechanisms?](https://mlsanity.com/paper/2609.31161/) (2026)
- [LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models](https://mlsanity.com/paper/2609.34375/) (2026)
- [Control-Geometry Straightening for Sampling-Based Latent Planning](https://mlsanity.com/paper/2609.35603/) (2026)
- [Do-JEPA: From Masking to Intervention in Latent World Models](https://mlsanity.com/paper/2609.37378/) (2026)
- [Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics](https://mlsanity.com/paper/2610.00280/) (2026)
- [Keeping JEPA World Models Plannable When Little of the Frame Moves](https://mlsanity.com/paper/2610.03137/) (2026)
- [LeCuration: A Tiny World Model as a Data Curation Multi-Tool](https://mlsanity.com/paper/2610.09285/) (2026)
- [CausalDreamer: Learning Predictive World Models with Latent Disentanglement](https://mlsanity.com/paper/2610.12016/) (2026)

## Abstract (arXiv)

World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not sufficient to capture interaction-dependent dynamics. We therefore propose C-JEPA, a simple and flexible object-centric world model that extends masked joint embedding prediction from image patches to object-centric representations. By masking object-level latents and requiring each masked object state to be inferred from the surrounding context, C-JEPA imposes structured partial observability during training, creating counterfactual-like prediction queries that discourage shortcut solutions and make interaction-dependent prediction necessary under the learning objective. Empirically, C-JEPA leads to consistent gains in visual question answering, with an absolute improvement of about 20% in counterfactual reasoning over the same architecture without object-level masking. On agent control tasks, C-JEPA enables substantially more efficient planning by using only 1% of the total latent input features required by patch-based world models, while achieving comparable performance. Finally, we provide a formal analysis demonstrating that object-level masking induces useful inductive bias by controlling observability. Our code is available at https://github.com/galilai-group/cjepa.