Imagen de Portada

Adapting World Models with Latent-State Dynamics Residuals

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lanier, JB, Kim, Kyungmin, Karamzade, Armin, Liu, Yifei, Sinha, Ankita, He, Kat, Corsi, Davide, Fox, Roy
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Model-Based Reinforcement Learning under Random Observation Delays
por: Karamzade, Armin, et al.
Publicado: (2025)

Reinforcement Learning from Delayed Observations via World Models
por: Karamzade, Armin, et al.
Publicado: (2024)

Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions
por: Kim, Kyungmin, et al.
Publicado: (2024)

Moonwalk: Inverse-Forward Differentiation
por: Krylov, Dmitrii, et al.
Publicado: (2024)

Realizable Continuous-Space Shields for Safe Reinforcement Learning
por: Kim, Kyungmin, et al.
Publicado: (2024)

ResWM: Residual-Action World Model for Visual RL
por: Zhang, Jseen, et al.
Publicado: (2026)

Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games
por: Lanier, JB, et al.
Publicado: (2026)

Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Models
por: Nachkov, Asen, et al.
Publicado: (2025)

Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
por: Zhang, Yang, et al.
Publicado: (2025)

Kinematics-Aware Latent World Models for Data-Efficient Autonomous Driving
por: Li, Jiazhuo, et al.
Publicado: (2026)

Learning Visual Feature-Based World Models via Residual Latent Action
por: Zhang, Xinyu, et al.
Publicado: (2026)

Efficient Dynamic Shielding for Parametric Safety Specifications
por: Corsi, Davide, et al.
Publicado: (2025)

Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving
por: Xiao, Lingyu, et al.
Publicado: (2024)

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
por: Chen, Zhongxi, et al.
Publicado: (2026)

Trust Region Q Adjoint Matching
por: Dong, Yonghoon, et al.
Publicado: (2026)

Chain of World: World Model Thinking in Latent Motion
por: Yang, Fuxiang, et al.
Publicado: (2026)

DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
por: Lyu, Jiangran, et al.
Publicado: (2025)

Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
por: Chi, Haozhuang, et al.
Publicado: (2026)

Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation
por: Nagahisa, Haruto, et al.
Publicado: (2026)

Efficient Real-World Autonomous Racing via Attenuated Residual Policy Optimization
por: Trumpp, Raphael, et al.
Publicado: (2026)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
por: Wang, Yiqi, et al.
Publicado: (2025)

Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
por: Kim, Dongwon, et al.
Publicado: (2026)

LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation
por: Huang, Yuhang, et al.
Publicado: (2025)

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
por: Wang, Ruixiang, et al.
Publicado: (2026)

Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
por: Duan, Yuanlin, et al.
Publicado: (2024)

Vehicle Dynamics Embedded World Models for Autonomous Driving
por: Li, Huiqian, et al.
Publicado: (2025)

Information-Theoretic Framework for Self-Adapting Model Predictive Controllers
por: Hafez, Wael, et al.
Publicado: (2026)

DiLA: Disentangled Latent Action World Models
por: Zhang, Tianqiu, et al.
Publicado: (2026)

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
por: Huang, Wenlong, et al.
Publicado: (2026)

Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning
por: Corsi, Davide, et al.
Publicado: (2024)

LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Model
por: Chen, Siwei, et al.
Publicado: (2023)

Shield Synthesis for LTL Modulo Theories
por: Rodriguez, Andoni, et al.
Publicado: (2024)

Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems
por: Li, Mingwei, et al.
Publicado: (2025)

RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC
por: Han, Seungho, et al.
Publicado: (2026)

AdaWorld: Learning Adaptable World Models with Latent Actions
por: Gao, Shenyuan, et al.
Publicado: (2025)

Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications
por: Foutter, Matthew, et al.
Publicado: (2024)

LatentMimic: Terrain-Adaptive Locomotion via Latent Space Imitation
por: Wang, Zhiquan, et al.
Publicado: (2026)

Residual Chain Prediction for Autonomous Driving Path Planning
por: Zhou, Liguo, et al.
Publicado: (2024)

Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models
por: Chen, Haonan, et al.
Publicado: (2025)

World-Gymnast: Training Robots with Reinforcement Learning in a World Model
por: Sharma, Ansh Kumar, et al.
Publicado: (2026)