7 papers
Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies
Andrew Ting Yan Li, Zhuo Li, Zhelin Yang +3
Vision-language-action (VLA) models are trained by imitation and capture what action to take but not why; adding causal reasoning improves manipulation, but current methods pay for…
Beyond Point-Attached Semantics: Stable Object-Centric Semantic Fields for Robust Manipulation
Zheng Sun, Lerong Zhang, Zhihao Li +3
Robotic manipulation often requires identifying functional parts, such as a mug handle or a hammer head. However, features attached to observed 3D points can vary with viewpoint an…
Adapt as You Say: Online Interactive Bimanual Skill Adaptation via Human Language Feedback
Zhuo Li, Dianxi Li, Tao Teng +5
Developing general-purpose robots capable of autonomously operating in human living environments requires the ability to adapt to continuously evolving task conditions. However, ad…
From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models
Zhuofan Li, Hongkun Yang, Zhenyang Chen +4
Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities.…
Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion
Zhuo Li, Junjia Liu, Zhipeng Dong +4
Vision-Language-Action (VLA) models have demonstrated significant potential in real-world robotic manipulation. However, pre-trained VLA policies still suffer from substantial perf…
ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation
Zhuo Li, Junjia Liu, Dianxi Li +5
Recent work has demonstrated the potential of diffusion models in robot bimanual skill learning. However, existing methods ignore the learning of posture-dependent task features, w…
Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration
Junjia Liu, Zhuo Li, Minghao Yu +4
Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuo…