NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
We present EB-JEPA, an open-source library for learning representations and world models using Joint-Embedding Predictive Architectures (JEPAs). JEPAs learn to predict in representation space rather than pixel space, avoiding the pitfalls of generative modeling while capturing semantically meaningful features suitable for downstream tasks. Our library provides modular, self-contained implementations that illustrate how representation learning techniques developed for image-level self-supervised learning can transfer to video, where temporal dynamics add complexity, and ultimately to action-conditioned world models, where the model must additionally learn to predict the effects of control inputs. Each example is designed for single-GPU training within a few hours, making energy-based self-supervised learning accessible for research and education. We provide ablations of JEA components on CIFAR-10. Probing these representations yields 91% accuracy, indicating that the model learns useful features. Extending to video, we include a multi-step prediction example on Moving MNIST that demonstrates how the same principles scale to temporal modeling. Finally, we show how these representations can drive action-conditioned world models, achieving a 97% planning success rate on the Two Rooms navigation task. Comprehensive ablations reveal the critical importance of each regularization component for preventing representation collapse. Code is available at https://github.com/facebookresearch/eb_jepa.
years
2026 5verdicts
UNVERDICTED 5representative citing papers
SMWM trains end-to-end latent world models from offline reward-free data using inverse dynamics regularization to prevent collapse and align states with controllable actions for planning.
DREAM-Chunk uses test-time sampling and latent-world-model rollouts to select robust action chunks from chunking-based VLA policies, improving performance under stochastic dynamics on simulation and hardware tasks.
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
Hierarchical latent world models with macro-actions solve long-horizon visual planning (70% Franka pick-and-place vs 0% flat planning) with up to 3× less compute.
citing papers explorer
-
Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
-
Sensorimotor World Models: Perception for Action via Inverse Dynamics
SMWM trains end-to-end latent world models from offline reward-free data using inverse dynamics regularization to prevent collapse and align states with controllable actions for planning.
-
DREAM-Chunk: Reactive Action Chunking with Latent World Model
DREAM-Chunk uses test-time sampling and latent-world-model rollouts to select robust action chunks from chunking-based VLA policies, improving performance under stochastic dynamics on simulation and hardware tasks.
-
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
-
Hierarchical Planning with Latent World Models
Hierarchical latent world models with macro-actions solve long-horizon visual planning (70% Franka pick-and-place vs 0% flat planning) with up to 3× less compute.