Cover Image

World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yuejiang, Feng, Fan, Kong, Lingjing, Lu, Weifeng, Tang, Jinzhou, Zhang, Kun, Murphy, Kevin, Finn, Chelsea, Du, Yilun
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Self-Guided Action Diffusion
by: Malhotra, Rhea, et al.
Published: (2025)

Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling
by: Liu, Yuejiang, et al.
Published: (2024)

Learning Long-Context Diffusion Policies via Past-Token Prediction
by: Torne, Marcel, et al.
Published: (2025)

VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
by: Guo, Yanjiang, et al.
Published: (2026)

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

Curating Demonstrations using Online Experience
by: Chen, Annie S., et al.
Published: (2025)

Ctrl-World: A Controllable Generative World Model for Robot Manipulation
by: Guo, Yanjiang, et al.
Published: (2025)

Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
by: Kwok, Jacky, et al.
Published: (2026)

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

Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model
by: Zhao, Chen, et al.
Published: (2026)

Point Tracking Improves World Action Models
by: Guan, Jiarui, et al.
Published: (2026)

To Err is Robotic: Rapid Value-Based Trial-and-Error during Deployment
by: Du, Maximilian, et al.
Published: (2024)

WorldVLA: Towards Autoregressive Action World Model
by: Cen, Jun, et al.
Published: (2025)

OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
by: Song, Yuxin Ray, et al.
Published: (2025)

RoboDreamer: Learning Compositional World Models for Robot Imagination
by: Zhou, Siyuan, et al.
Published: (2024)

Self-Improving Loops for Visual Robotic Planning
by: Luo, Calvin, et al.
Published: (2025)

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
by: Kim, Moo Jin, et al.
Published: (2025)

RISE: Self-Improving Robot Policy with Compositional World Model
by: Yang, Jiazhi, et al.
Published: (2026)

Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models
by: Wu, Qi, et al.
Published: (2024)

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

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
by: Dong, Perry, et al.
Published: (2026)

MotuBrain: An Advanced World Action Model for Robot Control
by: MotuBrain Team, et al.
Published: (2026)

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
by: Li, Hengtao, et al.
Published: (2025)

Scaling Cross-Embodiment World Models for Dexterous Manipulation
by: He, Zihao, et al.
Published: (2025)

Staircase Recognition and Location Based on Polarization Vision
by: Kong, Weifeng, et al.
Published: (2025)

Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation
by: Bo, Zitong, et al.
Published: (2025)

3D-VLA: A 3D Vision-Language-Action Generative World Model
by: Zhen, Haoyu, et al.
Published: (2024)

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
by: Yu, Dongjie, et al.
Published: (2026)

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
by: Li, Runze, et al.
Published: (2026)

FAST: Efficient Action Tokenization for Vision-Language-Action Models
by: Pertsch, Karl, et al.
Published: (2025)

Update-Free On-Policy Steering via Verifiers
by: Attarian, Maria, et al.
Published: (2026)

$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
by: Intelligence, Physical, et al.
Published: (2025)

PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
by: Zheng, Yupeng, et al.
Published: (2026)

NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social Navigation
by: Hu, Tianshuai, et al.
Published: (2026)

World Action Models are Zero-shot Policies
by: Ye, Seonghyeon, et al.
Published: (2026)

Grounding Video Models to Actions through Goal Conditioned Exploration
by: Luo, Yunhao, et al.
Published: (2024)

WorldPlanner: Monte Carlo Tree Search and MPC with Action-Conditioned Visual World Models
by: Khorrambakht, R., et al.
Published: (2025)

VLM-DEWM: Dynamic External World Model for Verifiable and Resilient Vision-Language Planning in Manufacturing
by: Tang, Guoqin, et al.
Published: (2026)

Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
by: Chi, Cheng, et al.
Published: (2023)

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