10 papers
Black-Box Adversarial Patch Attacks on VLAs via Ancestor VLM Exploitation
Xiaoyi Pang, Haoyue Feng, Quanxin Shou +3
Vision-Language-Action models (VLAs) are increasingly deployed in safety-critical physical environments, yet their adversarial robustness remains poorly understood. Existing attack…
World Action Learning via Interaction-Centric Spectral Latent Guidance
Zhiming Liu, Yikun Miao, Ying Chen +7
Learning general-purpose robot policies requires large-scale real-world interaction data, yet collecting robot demonstrations remains expensive and difficult to scale. Egocentric v…
SteerQuant: Steering Quantization Error with Action-Guided Scaling in World-Action Models
Yunhan Wang, Haodong Wang, Zhiming Liu +7
World-action models (WAMs) jointly generate future world states and actions through iterative denoising, using shared weights to process heterogeneous semantic streams of video, pr…
Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination
Xinling Xie, Haodong Wang, Jiazhi Mi +8
World-action models (WAMs) leverage pretrained video models to improve generalization in robot control by jointly predicting future visual states and actions. This capability comes…
OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling
Yikun Miao, Fangqi Zhu, Quanxin Shou +6
Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeling. While recent efforts levera…
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
Bohai Gu, Yueyang Yuan, Taiyi Wu +9
Interactive video world models are essential for long-horizon planning and exploration, yet they suffer from compounding errors. Post-training methods such as reinforcement learnin…
RedFlow: Redirect Failure into Action-level Corrections for Flow-matching VLA Policy
Zhengyang Yan, Junhao Li, Fangqi Zhu +6
Reinforcement learning (RL) can improve Vision-Language-Action (VLA) policies from deployment experience, but reward- and preference-based RL primarily identifies desirable behavio…
HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
Quanxin Shou, Fangqi Zhu, Shawn Chen +9
Vision-Language-Action (VLA) models have shown strong performance in robotic manipulation, but often struggle in long-horizon or out-of-distribution scenarios due to the lack of ex…
Generating Storytelling Images with Rich Chains-of-Reasoning
Xiujie Song, Qi Jia, Shota Watanabe +4
A single image can convey a compelling story through logically connected visual clues, forming Chains-of-Reasoning (CoRs). We define these semantically rich images as Storytelling…
Is Your Image a Good Storyteller?
Xiujie Song, Xiaoyi Pang, Haifeng Tang +2
Quantifying image complexity at the entity level is straightforward, but the assessment of semantic complexity has been largely overlooked. In fact, there are differences in semant…