World Action Models

Follow this topic Ask about this topic

Momentum

46 papers in the last four weeks, up 254% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 155

All topics

World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models
Sep 2, 2026Chuhan Zhang, Seiji Ito, Kenta Hoshino +2World Action Models Robotic Manipulation
Department of Computer Science Institute of Science Tokyo · DENSO IT Lab, Japan · National Institute of Informatics, Japan
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
Aug 31, 2026Xionghao Wu, Yijun Yang, Shiyang Zhou +17World Models for Robotics Generalization in Robotic Manipulation
Joy Future Academy
Latent Action as Intention Enables Efficient Future Imagination for World Action Models
Aug 25, 2026Xiang Li, Yupeng Zheng, Songen Gu +11Latent Action Learning World Models for Robotics
1CollegeAI, THU · 2AIR, THU · 4TARS Robotics +6
GlanceWAM: Sparse Test-Time Imagination for World-Action Models
Aug 25, 2026Linhan Wang, Zijian An, Mingyuan Zhang +8Efficient Inference for World Action Models Robotic Manipulation
Virginia Tech · Drexel University · Northeastern University +1
DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation
Aug 22, 2026Fenghao Lei, Zhixiong Huang, Long Yang +5Long-Horizon Robotic Manipulation World Models for Robotics
DeepLeap Research, Shenzhen, China
Foresight Without Seeing: Latent Futures for World Action Models
Aug 12, 2026Jiakai Huang, Zhongbo Wu, Siyu Xu +5World Models for Robotics Visuomotor Policy Learning
Shanghai Jiao Tong University · ACE Robotics · Nanyang Technological University
Keep the Future, Drop the Rollout: RIFT for World Action Models
Aug 12, 2026Chushan Zhang, Jinguang Tong, Xuesong Li +2Efficient VLA Model Inference Efficient Inference for World Action Models
Australian National University
Flex- $π$ : A Multi-Stream World-Action Model with Compute Flexibility
Aug 11, 2026Ge Yan, Jinghao Liu, Yuzhi Fan +4World Models World Model-Based Planning
University of Washington · Allen Institute for AI
FACT: Failure-Aware Causal Training for World-Action Models
Aug 10, 2026Quanquan Peng, Yutong Liang, Rui Yan +2Causal World Models Action-Conditioned World Models
University of California San Diego
4D-WAM: 4D Consistent World Modeling for Autonomous Driving
Aug 10, 2026Jiacheng Fu, Yibo Yuan, Meng Tian +8World Action Models World Models for Autonomous Driving
University of Science and Technology of China · Xi’an Jiaotong University · Yinwang Intelligent Technology Co., Ltd. +1
HarnessWAM: Bridging Prediction and Deliberation in World Action Models
Aug 10, 2026Zhaopeng Gu, Bingke Zhu, Tianxi Lin +8World Models for Robotics Large Language Model-Based Robot Planning
Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Yinwang Intelligent Technology Co., Ltd., Shenzhen, China +2
Rethink Before You Execute: Adaptive Execution for World Action Models
Aug 10, 2026Feng Ye, Yiming Zhao, Yong Yu +5World Models for Robotics LLM Planning
Wangxuan Institute of Computer Technology, Peking University · Simplexity Robotics
SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models
Aug 9, 2026Junjie He, Junfeng Li, Zhide Zhong +9World Models for Robotics Language-Conditioned Robot Manipulation
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Ola Dimensions, Shenzhen, China
Vid2WAM: Distilling Video Diffusion Priors into World Action Models
Aug 9, 2026Chenhao Qiu, Ruixiang Wang, Runyi Zhao +7Cross-Modal Knowledge Distillation World Model Learning
Fudan University · The Chinese University of Hong Kong, Shenzhen · Shanghai Innovation Institute
4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
Aug 8, 2026Lishan Yang, Wenxuan Song, Xi Wang +14World Models for Robotics Action-Conditioned World Models
Adelaide University · HKUST(GZ) · Tsinghua University +3
WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
Aug 7, 2026Yuehao Huang, Yunzi Wu, Xiaotao Zhang +7World Model Learning Vision-Language Navigation
Institute of Artificial Intelligence, China Telecom · 2Zhejiang University · 3Tongji University +1
Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models
Aug 7, 2026Xiangkai Ma, Yue Ma, Junjie Wang +6Robot Motion Generation Robotic Manipulation
1NJU · 2HKUST · 3CUHK-SZ +4
$ω$ -0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation
Aug 6, 2026Zhe Li, Zhenzhe Zhang, Yangyang Wei +8Humanoid Loco-Manipulation Language-Conditioned Robot Manipulation
MARS Lab, NTU · BAAI · PKU +1
Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models
Aug 6, 2026Haodong Yan, Junfeng Li, Junjie He +12Domain Generalization World Action Models
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Beihang University, Beijing, China · Huawei Foundation Model Department
DreamWAM: Beyond RGB Future Prediction for World Action Models
Aug 5, 2026Shanglin Yuan, Weiheng Zhao, Xin Shi +6World Model Learning Action-Conditioned World Models
Huazhong University of Science and Technology · D-Robotics · Wuhan University +1
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
Aug 5, 2026Zehua Fan, Junjie He, Wenxuan Song +14World Models for Robotics Mobile Manipulation
Institute for AI Industry Research (AIR), Tsinghua University · 2Shanghai Jiao Tong University · 3The Hong Kong University of Science and Technology (Guangzhou) +8
Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models
Aug 5, 2026Weiheng Zhao, Haoyi Jiang, Xin Shi +5Action-Conditioned World Models Efficient VLA Model Inference
Huazhong University of Science and Technology · D-Robotics · Horizon Robotics +1
LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation
Aug 4, 2026Fan Yang, Yuting Su, Xiaobo Wang +7World Models for Robotics Latent Visual Reasoning
1Tianjin University · 2Shenzhen University of Advanced Technology · 5Sangfor Technologies Inc. +2
Faster-WAM: Do World Action Models Need Deep Action Modules?
Aug 3, 2026Liheng Ma, Rui Heng Yang, Amin Abyaneh +8World Model Learning Efficient Inference for World Action Models
Huawei Noah’s Ark Lab
World Action Models in Real Time: An Empirical Study of Smooth Execution via Asynchronous Deployment
Aug 3, 2026Motubrain TeamWorld Action Models Action Chunking
SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space
Aug 2, 2026Ruiteng Zhao, Zhengshen Zhang, Yue Su +6World Models for Robotics Action-Conditioned World Models
Advanced Robotics Centre, National University of Singapore · Singapore Institute of Manufacturing Technology, Agency for Science, Technology and Research (A*STAR) · MMLab, The University of Hongkong
EndoWAM: A Grounded World-Action Model for Generalizable Endoscopic Navigation
Aug 2, 2026Jinsong Lin, Zikang Pan, Wanhao Liu +10World Models for Robotics World Action Models
CUHK · SLAI · WFU +3
SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control
Aug 1, 2026Bikang Pan, Fan Liu, Haotao Lu +2Action-Conditioned Video Generation World Models for Robotics
1ShanghaiTech University · 2InstAdapt
FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution
Jul 31, 2026Peize Li, Ruimeng Zhang, Ru Zhang +3Flow Matching World Models for Robotics
DeepCybo · Zhongguancun Academy · Zhongguancun Institute of Artificial Intelligence +3
ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts
Jul 31, 2026Mingxin Wang, Bin Hu, Bin Qian +12World Models for Robotics Generalization in Robotic Manipulation
1Tsinghua University · 2AMAP-CV-LAB, Alibaba Group · 3Shanghai Jiao Tong University +3

Sep 2, 2026, cs.CVJ/K move · Enter open · S save

World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models

Chuhan Zhang, Seiji Ito, Kenta Hoshino, Satoshi Ikehata+1

Department of Computer Science Institute of Science Tokyo · DENSO IT Lab, Japan · National Institute of Informatics, Japan

World Action Models Robotic Manipulation

Open paper AskPDF arXiv

World Action Models (WAMs) aim to control robots by stochastically generating visual futures and then decoding actions, but empirical observations indicate that the results can strongly depend on which future is selected. We propose World-Coherent-Decoding (WCD), a self-verifying test-time planning framework that treats WAM rollouts as falsifiable future--action hypotheses. At each decision step, WCD samples multiple candidates from a frozen WAM and ranks them using internal generative signals: flow-based video surprisal for visual plausibility and action path effort for action-generation stability. After execution, the realized observation audits the selected imagination, yielding an imagination--reality mismatch that trains a lightweight online predictor for future candidate selection. Thus, WCD converts delayed self-verification into pre-execution reliability estimation without updating the backbone model. On RoboTwin 2.0, WCD improves Hard success under limited randomized-scene supervision from

55.80\%

60.90\%

, with a

+16.43

gains on Horizon-3 tasks, and shows qualitative robustness on real Franka visual-shift tests. These results highlight a simple principle: test-time scaling for WAMs depends less on sampling more futures than on selecting reliable ones.

Momentum

Related topics

Latest papers 155