LeJEPA achieves linear identifiability of latent variables uniquely when the latents are Gaussian in worlds with stationary additive-noise transitions.
Causal- jepa: Learning world models through object-level latent interventions
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
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.
citation-role summary
background 1
citation-polarity summary
years
2026 12roles
background 1polarities
background 1representative citing papers
Goal-conditioned world models transcribe instructions instead of perceiving spatial relations when the instruction names the scored quantity, and removing the goal from the dynamics fixes it.
VLWMs learn variable-length action-conditioned dynamics in latent space with curriculum training, yielding 13% average gains over prior latent world models on long-horizon tasks.
Cross-trajectory negative sampling in contrastive predictive objectives causes encoding of slow noise over dynamics; intra-trajectory sampling eliminates the shortcut and recovers dynamical variables even under strong noise.
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
Neuro-JEPA, a JEPA-and-MoE transformer pretrained on 1.55M brain MRI scans, outperformed prior neuroimaging foundation models and was the only one to beat a simple CNN baseline on average.
Loop-OWM uses color-prototype slots, demonstration-conditioned task summaries, and looped transitions to model ARC rules as visual-symbolic state changes and outperforms baselines on ARC-1 and ARC-2.
Slot-MPC learns slot representations to build a differentiable object-centric dynamics model that supports efficient gradient-based MPC for robotic manipulation in novel situations.
LeWM is a ~15M-parameter JEPA world model that trains end-to-end from pixels with only next-embedding prediction plus a Gaussian latent regularizer, cutting loss hyperparameters to one.
Einstein World Models integrate visual rollouts from a callable world-module into LLM reasoning traces to support complex thought beyond language.
CausalVAE plug-in for world models preserves factual prediction and boosts counterfactual retrieval, with large gains on physics benchmarks and recovered physical interaction trends.
citing papers explorer
-
When Does LeJEPA Learn a World Model?
LeJEPA achieves linear identifiability of latent variables uniquely when the latents are Gaussian in worlds with stationary additive-noise transitions.
-
Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix
Goal-conditioned world models transcribe instructions instead of perceiving spatial relations when the instruction names the scored quantity, and removing the goal from the dynamics fixes it.
-
Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning
VLWMs learn variable-length action-conditioned dynamics in latent space with curriculum training, yielding 13% average gains over prior latent world models on long-horizon tasks.
-
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
Cross-trajectory negative sampling in contrastive predictive objectives causes encoding of slow noise over dynamics; intra-trajectory sampling eliminates the shortcut and recovers dynamical variables even under strong noise.
-
Latent State Design for World Models under Sufficiency Constraints
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
-
Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging
Neuro-JEPA, a JEPA-and-MoE transformer pretrained on 1.55M brain MRI scans, outperformed prior neuroimaging foundation models and was the only one to beat a simple CNN baseline on average.
-
Slots, Transitions, Loops: Learning Composable World Models for ARC
Loop-OWM uses color-prototype slots, demonstration-conditioned task summaries, and looped transitions to model ARC rules as visual-symbolic state changes and outperforms baselines on ARC-1 and ARC-2.
-
Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations
Slot-MPC learns slot representations to build a differentiable object-centric dynamics model that supports efficient gradient-based MPC for robotic manipulation in novel situations.
-
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
LeWM is a ~15M-parameter JEPA world model that trains end-to-end from pixels with only next-embedding prediction plus a Gaussian latent regularizer, cutting loss hyperparameters to one.
-
Einstein World Models
Einstein World Models integrate visual rollouts from a callable world-module into LLM reasoning traces to support complex thought beyond language.
-
CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics
CausalVAE plug-in for world models preserves factual prediction and boosts counterfactual retrieval, with large gains on physics benchmarks and recovered physical interaction trends.
- Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers