World Models for VLA Models

VLA: Vision-Language-Action

Follow this topic Ask about this topic

Latest papers

47 papers20 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models
Sep 3, 2026Chenhao Zhang, Hanyu Zhao, Hang Cheng +2Robustness of VLA Models World Models for Robotics
1Tsinghua University · 2Beijing Academy of Artificial Intelligence (BAAI)
AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies
Aug 15, 2026An Lanji, Dawei Liu, Jin Li +3World Models for VLA Models Vision-Language-Action Models
University of Electronic Science and Technology of China, Chengdu, China.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
Aug 10, 2026Qu Tang, Benhui Zhuang, Bo Yuan +3Efficient VLA Model Inference Efficient VLA Models
JIUTIAN Research · Zhongguancun Academy
GWM-VLA: Geometry-Aware Latent World Modeling for Vision-Language-Action Learning
Aug 7, 2026Yanping Zhao, Hang Yu, Yiwei Wang +8World Model Learning Robotic Manipulation
Tongji University
WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning
Jul 31, 2026Senyu Fei, Xiaopeng Yu, Siyin Wang +3World Model Learning Vision-Language-Action Models
1Tongji University · 3Fudan University · 2Shanghai Innovation Institute
World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models
Jul 30, 2026Xiangcheng Zhang, Yilun DuWorld Models for Robotics World Model-Based Planning
Harvard University
WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling
Jul 3, 2026Zelin Zhao, Min Shi, Bo Yuan +5World Models for Robotics Unified Multimodal Models
Georgia Institute of Technology
FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation
Jun 29, 2026Lingfeng Zhang, Zeying Gong, Xiaoshuai Hao +7World Models Vision-Language Navigation
Tsinghua University · Pengcheng Laboratory · Xiaomi EV +2
World Pilot: Steering Vision-Language-Action Models with World-Action Priors
Jun 10, 2026Zefu Lin, Rongxu Cui, Junjia Xu +4Zero-Shot Robotic Manipulation World Models for Robotics
Institute of Automation, Chinese Academy of Sciences (CASIA) · Nanjing University · Beihang University
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
Jun 4, 2026Yi Yang, Zhihong Liu, Siqi Kou +9World Models for Robotics Robot Foundation Models
SJTU · SII · HUST +4
World Action Models: The Next Frontier in Embodied AI
May 12, 2026Siyin Wang, Junhao Shi, Zhaoyang Fu +11Vision-Language-Action Models World Action Models
1Fudan University · 2Shanghai Innovation Institute · 3National University of Singapore
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
May 8, 2026Zuojin Tang, Shengchao Yuan, Xiaoxin Bai +4Visual Token Compression Efficient VLA Models
Zhejiang University · Central South University · Harbin Institute of Technology +2
Grounded World Model: Latent Planning with Language Goals
Apr 13, 2026Quanyi Li, Lan Feng, Haonan Zhang +4Language-Conditioned Robot Planning World Models for Robotics
EPFL · NUS
Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
Mar 21, 2026Zhilong Zhang, Haoxiang Ren, Yihao Sun +6RL for VLMs Vision-Language-Action Models
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · School of Artificial Intelligence, Nanjing University, Nanjing, China · Mila - Quebec AI Institute +1
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
Mar 19, 2026Chengxuan Lu, Shukuan Wang, Yanjie Li +10World Models for VLA Models Asynchronous RL
IROOTECH TECHNOLOGY Wolf 1069 b Lab, Sany Group
World2Act: Latent Action Post-Training from World Model Dynamics
Mar 11, 2026An Dinh Vuong, Tuan Van Vo, Abdullah Sohail +6VLA Model Post-Training Vision-Language-Action Models
MBZUAI
Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation
Mar 2, 2026Jisoo Kim, Jungbin Cho, Sanghyeok Chu +9World Models for VLA Models Vision-Language-Action Models
KAIST AI · LG AI Research · Yonsei University +2

Sep 3, 2026J/K move · Enter open · S save

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models

Chenhao Zhang, Hanyu Zhao, Hang Cheng, Tengfei Pan+1

1Tsinghua University · 2Beijing Academy of Artificial Intelligence (BAAI)

Robustness of VLA Models World Models for Robotics World Model-Based Planning Vision-Language-Action Models Robot Skill Learning Efficient VLA Models+3

Open paper AskPDF arXiv

Post-training VLA policies typically rely on supervised fine-tuning with costly expert demonstrations or reinforcement learning with expensive and potentially unstable real-world exploration. World models offer a promising alternative by evaluating candidate behaviors through imagined futures, yet effective post-training requires more than accurate prediction: imagination must be scheduled where it is useful, bounded within reliable horizons, and translated into trustworthy policy supervision. In robotic manipulation, the value of imagination varies substantially across execution stages, while extended rollouts can accumulate prediction errors and introduce unreliable learning signals. We introduce WISE (World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models), a unified framework that coordinates when and how world-model imagination is used during policy refinement. WISE selectively invokes imagination at interaction-relevant states, performs bounded multi-view rollouts, evaluates candidate futures using progress and completion signals, and uses their relative outcomes to refine actions generated from real interaction contexts. Extensive experiments with both

π_0

and

π_{0.5}

demonstrate consistent improvements across diverse manipulation tasks while reducing GPU computation time by approximately 80% compared with full imagination. Real-world evaluations further show substantial gains in robustness and generalization under diverse real-world distribution shifts.