8 papers
WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity
Yuxue Yang, Shuyao Shang, Jiahe Wang +13
Controllable video generation models are increasingly being developed as world models. Accordingly, evaluating them in this role extends beyond the apparent appearance of generated…
Self-Evolving Just-In-Time Memory for Proactive Embodied Safety
Bingrui Sima, Lizhong Wang, Xiaoya Lu +2
While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during close…
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
Lingxuan Wu, Zijian Zhu, Lizhong Wang +5
Diffusion policies have achieved remarkable success in robotic manipulation, yet they often fail to satisfy strict physical constraints required for safe deployment. Existing appro…
FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning
Haihao Lin, Xiangsheng Huang, Xiao Yang +7
Action-supervised fine-tuning of vision-language-action (VLA) policies can compress visual structure that is weakly constrained by the action objective. We formalize this as residu…
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
Min Zhao, Hongzhou Zhu, Bokai Yan +13
Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains…
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
Jiachun Jin, Zetong Zhou, Xiao Yang +4
Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs…
Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents
Renhua Ding, Xiao Yang, Zhengwei Fang +3
Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remains underexplored. While agents are vuln…
Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models
Renhua Ding, Xinze Zhang, Xiao Yang +1
Although vision-language pre-training (VLP) models have achieved remarkable progress on cross-modal tasks, they remain vulnerable to adversarial attacks. Using data augmentation an…