arXiv Machine Learning
Enhancing Latent World Models with Associative Memory
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 18
Hierarchical Planning with Latent World Models
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
arXiv AI
4d ago
Exploring Temporal Context-Aware Physical Grounding in Latent World Models
arXiv:2610.28483v1 Announce Type: new Abstract: Learning latent dynamics is fundamental to building action-conditioned world models for planning. Among existing families, Joint Embedding Predictive A...
Hugging Face Trending Papers
4d ago
Exploring Temporal Context-Aware Physical Grounding in Latent World Models
Learning latent dynamics is fundamental to building action-conditioned world models for planning. Among existing families, Joint Embedding Predictive Architectures (JEPAs) offer a natural framework by...
arXiv AI
Jul 21
SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning
arXiv:2607. 17973v1 Announce Type: new Abstract: Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences.
arXiv Machine Learning
Sep 7
Spectral-Target Physical Latent Structuring for JEPA-Style World Models
The paper introduces a lightweight Fourier auxiliary head to enforce physically-informed structuring of latent states in JEPA-style world models, addressing a newly identified failure mode called physical representation laziness that hampers planning in dynamic environments. Experiments show that this auxiliary supervision improves planning success rates, enhances latent space correlations with key physical properties, and boosts data efficiency, even when the baseline model does not exhibit laziness.
arXiv AI
Jun 9
FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
arXiv:2606. 09311v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods like the Cross-Entropy Method (CEM).