Vision-Language-Action models (VLAs) are increasingly deployed in safety-critical physical environments, yet their adversarial robustness remains poorly understood. Existing attacks typically assume white-box access or rely on surrogate VLAs, which rarely holds in real-world deployments. Our key insight is that most VL...
Xiao-Yi Pang, Hao-Yue Feng, Quan-Xin Shou et al.· 0 citations
Results show that interaction-centric spectral guidance provides an effective and scalable way to transfer physical interaction knowledge from human egocentric video to robot control.
Zhi-Ming Liu, Yi-Kun Miao, Ying Chen et al.· 1 citation
SteerQuant, a 4-bit quantization framework for WAMs that steers errors toward computations with less influence on final actions, is introduced and Rudder, a 4-bit inference engine for WAMs that fuses scaling and output compensation into low-bit kernels is developed.
Yun-Han Wang, Hao-Dong Wang, Zhi-Ming Liu et al.· arXiv.org· 0 citations
Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeling. While recent efforts leverage simulator-generated data to enhance this capability, existing training pipelines face two fundamental limitations. First, static offline...
Yi-Kun Miao, Fang-Qi Zhu, Quan-Xin Shou et al.· 2 citations
This work introduces RedFlow, an offline post-training method for flow-matching VLA policies that requires neither external HIL corrections nor online data collection during post-training, and improves average success across four LIBERO suites.