Tag
H-JEPА introduces an action-conditioned joint-embedding predictive architecture that separates a wide perceptual code from an inherited control state governed by dissipative port-Hamiltonian dynamics, using port-inverse consistency as a parameter-free reweighting of prediction error, and matches or beats baselines like Delta-JEPA on pixel-based control benchmarks.
This paper proposes a composite-gradient learning method that integrates deep reinforcement learning and model predictive control for shared control authority in autonomous systems, with evaluations on traffic networks showing modest benefits under strong interaction.
Introduces Latent Energy Action Planning (LEAP), which optimizes action sequences through a frozen world model to improve goal-conditioned control, achieving a 17.3 percentage-point improvement in success rate across four control domains.
This paper introduces decision-metric alignment diagnostics and action-conditioned objectives to improve latent world models for model-predictive control. The proposed DA-LeWM method enhances convergence and success rates in planning tasks.
Proposes temporal-distance JEPA (TD-JEPA) which mines directed temporal cost from offline trajectories to improve latent world model predictive control, achieving higher success rates on robotic environments.
This paper presents a goal-agnostic control framework for partial differential equations using a joint-embedding predictive architecture (JEPA) with a lightweight 2D ViT encoder and action-conditioned latent dynamics, showing that using a learned physical observable probe outperforms raw latent distance for control tasks.
This paper introduces EHR-MPC, a framework that decouples learning patient dynamics from treatment optimization by training a generative digital twin of patients using electronic health records, then applying model predictive control at inference time, achieving comparable or improved performance over RL baselines on a multi-hospital sepsis cohort.
AdaJEPA introduces an adaptive latent world model that continuously updates during test-time via closed-loop model predictive control, significantly improving planning success under distribution shift.
Valdi combines end-to-end online training with latent diffusion dynamics for fast, uncertain dynamics prediction in model predictive control for reinforcement learning, showing preliminary results on the CarRacing environment.
This paper introduces BeliefDiffusion, a framework combining diffusion models to represent multimodal belief distributions and Model Predictive Control for planning in partially observable environments, achieving better navigation success and path efficiency than baselines.
This paper presents a skill-constrained model predictive control approach for resilient manufacturing supply chains, where training decisions affect future certified capacity. The controller solves a finite-horizon mixed-integer program and is evaluated on synthetic scenarios, showing that predictive control helps when bottlenecks are forecastable but is not universally superior.