11 papers · 1 filter
Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics
Songhua Yang, Ziyu Liu, Yuanwei Liu +5
Recently, Vision-Language-Action (VLA) models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understanding, and action generation in…
ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models
Songhua Yang, Ziyu Liu, Xuetao Li +3
Vision-Language-Action (VLA) policies are commonly adapted to new manipulation settings through additional gradient updates, which limits rapid deployment when task-specific data o…
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
Pinhan Fu, Xianda Guo, Xuetao Li +5
Vision-Language-Action (VLA) models are deployed through pipelines that end users cannot audit, and a poisoned VLA can behave normally on clean observations while a small visual tr…
Co-policy: Responsive Human-Robot Co-Creation for Musical Performances
Xuetao Li, Wenke Huang, Mang Ye +4
Art has long stood as a pivotal expression of human creativity. Embodied artificial intelligence offers a route for generative models to participate in that creativity through phys…
EDT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation
Kaiyan Zhao, Borong Zhang, Yiming Wang +4
In reinforcement learning (RL) for robotic manipulation, the Decision Transformer (DT) has emerged as an effective framework for addressing long-horizon tasks. However, DT's perfor…
Bridging Speech, Emotion, and Motion: a VLM-based Multimodal Edge-deployable Framework for Humanoid Robots
Songhua Yang, Xuetao Li, Xuanye Fei +2
Effective human-robot interaction requires emotionally rich multimodal expressions, yet most humanoid robots lack coordinated speech, facial expressions, and gestures. Meanwhile, r…
When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual Tokens
Xuetao Li, Pinhan Fu, Wenke Huang +7
Downstream fine-tuning of vision-language-action (VLA) models enhances robotics, yet exposes the pipeline to backdoor risks. Attackers can pretrain VLAs on poisoned data to implant…
Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation
Xuetao Li, Wenke Huang, Mang Ye +4
Humanoid robot manipulation is a crucial research area for executing diverse human-level tasks, involving high-level semantic reasoning and low-level action generation. However, pr…
RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation
Xuetao Li, Wenke Huang, Nengyuan Pan +7
Humanoid robots exhibit significant potential in executing diverse human-level skills. However, current research predominantly relies on data-driven approaches that necessitate ext…
DexFlow: A Unified Approach for Dexterous Hand Pose Retargeting and Interaction
Xiaoyi Lin, Kunpeng Yao, Lixin Xu +4
Despite advances in hand-object interaction modeling, generating realistic dexterous manipulation data for robotic hands remains a challenge. Retargeting methods often suffer from…
Learning Robust Grasping Strategy Through Tactile Sensing and Adaption Skill
Yueming Hu, Mengde Li, Songhua Yang +3
Robust grasping represents an essential task in robotics, necessitating tactile feedback and reactive grasping adjustments for robust grasping of objects. Previous research has ext…