Copertina

ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Peng, Baorui, Zhang, Wenyao, Xu, Liang, Qi, Zekun, Zhang, Jiazhao, Liu, Hongsi, Zeng, Wenjun, Jin, Xin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Robotics Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
di: Zhang, Wenyao, et al.
Pubblicazione: (2025)

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
di: Xu, Tianyu, et al.
Pubblicazione: (2025)

Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
di: Zhang, Wenyao, et al.
Pubblicazione: (2026)

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
di: Sun, Jingwen, et al.
Pubblicazione: (2026)

RoboScape: Physics-informed Embodied World Model
di: Shang, Yu, et al.
Pubblicazione: (2025)

Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model
di: Xu, Wenjiang, et al.
Pubblicazione: (2025)

WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
di: Shang, Yu, et al.
Pubblicazione: (2026)

WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
di: Shang, Yu, et al.
Pubblicazione: (2026)

MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving
di: Liu, Hongsi, et al.
Pubblicazione: (2024)

EVA: An Embodied World Model for Future Video Anticipation
di: Chi, Xiaowei, et al.
Pubblicazione: (2024)

Rethinking Video Generation Model for the Embodied World
di: Deng, Yufan, et al.
Pubblicazione: (2026)

ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark
di: Dang, Ronghao, et al.
Pubblicazione: (2025)

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

GigaWorld-0: World Models as Data Engine to Empower Embodied AI
di: GigaWorld Team, et al.
Pubblicazione: (2025)

The Safety Challenge of World Models for Embodied AI Agents: A Review
di: Baraldi, Lorenzo, et al.
Pubblicazione: (2025)

TesserAct: Learning 4D Embodied World Models
di: Zhen, Haoyu, et al.
Pubblicazione: (2025)

Reasoning in Space via Grounding in the World
di: Chen, Yiming, et al.
Pubblicazione: (2025)

Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
di: Xu, Mutian, et al.
Pubblicazione: (2026)

STORM: Search-Guided Generative World Models for Robotic Manipulation
di: Lin, Wenjun, et al.
Pubblicazione: (2025)

Learning 3D Persistent Embodied World Models
di: Zhou, Siyuan, et al.
Pubblicazione: (2025)

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks
di: Lin, Zuyao, et al.
Pubblicazione: (2026)

SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
di: He, Ziheng, et al.
Pubblicazione: (2026)

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
di: Zhang, Wenyao, et al.
Pubblicazione: (2025)

DexVLG: Dexterous Vision-Language-Grasp Model at Scale
di: He, Jiawei, et al.
Pubblicazione: (2025)

BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks
di: Chen, Yixiang, et al.
Pubblicazione: (2026)

OctoNav: Towards Generalist Embodied Navigation
di: Gao, Chen, et al.
Pubblicazione: (2025)

Is Your Driving World Model an All-Around Player?
di: Kong, Lingdong, et al.
Pubblicazione: (2026)

GeoWorld: Geometric World Models
di: Zhang, Zeyu, et al.
Pubblicazione: (2026)

Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
di: Zhang, Jiazhao, et al.
Pubblicazione: (2024)

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
di: Liu, Xinhao, et al.
Pubblicazione: (2025)

From Perfect to Noisy World Simulation: Customizable Embodied Multi-modal Perturbations for SLAM Robustness Benchmarking
di: Xu, Xiaohao, et al.
Pubblicazione: (2024)

World Action Models: The Next Frontier in Embodied AI
di: Wang, Siyin, et al.
Pubblicazione: (2026)

OmniNWM: Omniscient Driving Navigation World Models
di: Li, Bohan, et al.
Pubblicazione: (2025)

RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
di: Tang, Yinzhou, et al.
Pubblicazione: (2025)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
di: Liu, Jiahang, et al.
Pubblicazione: (2025)

WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
di: Zhao, Baining, et al.
Pubblicazione: (2026)

Occupancy World Model for Robots
di: Zhang, Zhang, et al.
Pubblicazione: (2025)

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning
di: Zhou, Heng, et al.
Pubblicazione: (2026)

ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
di: Chen, Yuzhi, et al.
Pubblicazione: (2026)

Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
di: Escoriza, Adrià López, et al.
Pubblicazione: (2025)