Plaintiffs in a federal lawsuit filed in California allege that the Department of Homeland Security revoked their Global Entry privileges in retaliation for exercising their constitutional rights.

Contextual Markov Decision Processes (cMDP) model this challenge, but existing methods often require explicit context variables (e.g., friction, gravity), limiting their use when contexts are latent or hard to measure. We introduce Dynamics-Aligned Latent Imagination (DALI), a framework integrated within the Dreamer architecture that infers latent context representations from agent-environment interactions. By training a self-supervised encoder to predict forward dynamics, DALI generates actionable representations conditioning the world model and policy, bridging perception and control. We theoretically prove this encoder is essential for efficient context inference and robust generalization. DALI's latent space enables counterfactual consistency: Perturbing a gravity-encoding dimension alters imagined rollouts in physically plausible ways. On challenging cMDP benchmarks, DALI achieves significant gains over contextunaware baselines, often surpassing context-aware baselines in extrapolation tasks, enabling zero-shot generalization to unseen contextual variations.

Perceiving the pre-eminence of image reconstruction in representation learning, we propose SMG (Separated Models for Generalization), a novel approach that exploits image reconstruction for generalization.

We introduce the Distributed-order fRActional Graph Operating Network (DRAGON), a novel continuous Graph Neural Network (GNN) framework that incorporates distributed-order fractional calculus.

Deep reinforcement learning (RL) is notoriously impractical to deploy due to sample inefficiency.

Their performance is well measured by the cross-entropy (CE) of the model distribution relative to the data distribution.

Basedontheseprinciples, weproposethe Distributed Morphological Attention Policy (DMAP) architecture (Figure 1). Weproposea Distributed Morphological Policy (DMAP) toaddressthisproblem (Figure 1).

Visual Reinforcement Learning (RL) agents trained on limited views face significant challenges in generalizing their learned abilities to unseen views.