arXiv AI
From Complex Histories to Simple Predictors: Predictive Dimension in Dynamic Graph Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 26
A Generalization Theory for JEPA-Based World Models
arXiv:2606. 27014v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have recently emerged as a promising paradigm for world modeling by learning predictive dynamics in a latent space rather than generating future observations at the input level.
arXiv Machine Learning
Oct 27
DT-JEPA: Learning to Predict Future Representations for Decision-Making
arXiv:2610.32657v1 Announce Type: new Abstract: Decision Transformer (DT) has demonstrated strong performance in various offline reinforcement learning (RL) tasks by conditioning action generation on...
arXiv Machine Learning
Jul 17
What Do Temporal Graph Learning Models Learn?
arXiv:2510. 09416v4 Announce Type: replace Abstract: Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models.
arXiv Machine Learning
Oct 3
Learning Commute-Time-Preserving World Models for Planning
The paper introduces Commute-Time-Preserving World Models (CTWMs), which learn latent representations that reflect commute-times in an environment by using a latent displacement predictor and a log-determinant regularizer. This approach addresses the issue that existing self-supervised methods degrade the necessary eigenvalue-dependent scaling for accurate commute-time representation. In experiments, CTWMs outperform the task-agnostic baseline LeWM on several continuous goal-reaching benchmarks while using only half the parameters.
arXiv Machine Learning
Oct 15
Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context
arXiv:2610.19364v1 Announce Type: new Abstract: Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do...
arXiv Machine Learning
Aug 27
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
The paper introduces Regularized Latent Dynamics Prediction (RLDP), a method that adds orthogonality regularization to self‑supervised next‑state prediction in latent space. RLDP maintains feature diversity, matching or surpassing complex representation learning approaches for zero‑shot reinforcement learning. It also performs robustly in low‑coverage data settings where prior methods fail.