JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
hub
Leworldmodel: Stable end-to-end joint-embedding predictive archi- tecture from pixels
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
years
2026 19representative citing papers
Masked-position MLM plus JEPA latent prediction outperforms MLM-only pretraining on 10-11 of 16 downstream tasks for 35M-150M protein models while JEPA alone fails.
AGWM improves world model accuracy in compositional environments by learning an explicit DAG of action affordance prerequisites to handle dynamic executability.
NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
3D-ALP achieves 0.65 success on memory-dependent 5-step robotic reach tasks versus near-zero for reactive baselines by anchoring MCTS planning to a persistent 3D camera-to-world frame.
Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.
RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.
AeroJEPA applies joint-embedding predictive learning to produce scalable, semantically organized latent representations for 3D aerodynamic fields that support both field reconstruction and downstream design tasks.
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
DySIB recovers a two-dimensional representation matching the phase space of a physical pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.
Sonata is a small hybrid world model pre-trained to predict future IMU states that outperforms autoregressive baselines on clinical discrimination, fall-risk prediction, and cross-cohort transfer while fitting on-device wearables.
IntentScore learns intent-conditioned action scores from offline GUI trajectories and raises task success by 6.9 points on an unseen agent and environment.
Metriplector treats neural computation as coupled metriplectic field dynamics whose stress-energy tensor readout achieves competitive results on vision, control, Sudoku, language modeling, and pathfinding with small parameter counts.
Video generation models can function as world simulators if efficiency gaps in spatiotemporal modeling are bridged via organized paradigms, architectures, and algorithms.
Action-state consistency in World Action Models distinguishes successful from failed imagined futures and supports value-free selection of better rollouts via consensus among predictions.
ST-Gen4D uses a world model that fuses global appearance and local dynamic graphs into a 4D cognition representation to guide consistent 4D Gaussian generation.
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.
A comprehensive survey that organizes the literature on world models in robot learning, their roles in policy learning, planning, simulation, and video-based generation, with connections to navigation, driving, datasets, and benchmarks.
citing papers explorer
-
Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data
DySIB recovers a two-dimensional representation matching the phase space of a physical pendulum from high-dimensional video data by maximizing predictive mutual information in latent space.