arXiv Machine Learning July 17, 2026 By Qi Li, Xingyi Yang, Xinchao Wang

BadWAM: When World-Action Models Dream Right but Act Wrong

Read the original on arXiv Machine Learning →

arXiv:2607. 15207v1 Announce Type: new Abstract: World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 16

ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control

arXiv:2606. 16605v1 Announce Type: new Abstract: World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making.

By Junjian Zhang, Hao Tan, Ruonan Li, Dong Zhu, Aiping Li, Zhaoquan Gu

agents robotics benchmarks safety

Hugging Face Trending Papers

Jul 30

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedback into physical action.

robotics safety

arXiv AI

Jun 10

Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies

arXiv:2606. 10371v1 Announce Type: cross Abstract: Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adversarial manipulation.

By Zi Yin, Peilin Chai, Siyuan Huang, Zhanhao Hu

llms diffusion robotics safety

arXiv AI

Aug 5

Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking

arXiv:2608. 03231v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies promise general robotic manipulation, but their robustness against physical-world attacks remains fragile.

By Jinquan Zhang, Dongfu Yin, Run Yang, Yufeng Yan, Zhen Tian, F. Richard Yu

robotics fine-tuning multimodal safety

arXiv Machine Learning

Jun 18

Stealthy World Model Manipulation via Data Poisoning

arXiv:2606. 18697v1 Announce Type: new Abstract: Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments.

By Yibin Hu, Xiaolin Sun, Zizhan Zheng

agents robotics fine-tuning safety

arXiv AI

5d ago

UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models

arXiv:2608. 13453v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks.

By Yukun Dai, Mingzhe Dai, Tianshi Wang, Fengling Li, Jingjing Li, Lei Zhu

agents robotics multimodal safety

Related stories

ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies

Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking

Stealthy World Model Manipulation via Data Poisoning

UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models