6 papers
REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching
Yinji Ge, Guixu Zheng, Wulong Guo +5
Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental…
LensDFF: Language-enhanced Sparse Feature Distillation for Efficient Few-Shot Dexterous Manipulation
Qian Feng, David S. Martinez Lema, Jianxiang Feng +2
Learning dexterous manipulation from few-shot demonstrations is a significant yet challenging problem for advanced, human-like robotic systems. Dense distilled feature fields have…
DexGANGrasp: Dexterous Generative Adversarial Grasping Synthesis for Task-Oriented Manipulation
Qian Feng, David S. Martinez Lema, Mohammadhossein Malmir +4
We introduce DexGanGrasp, a dexterous grasping synthesis method that generates and evaluates grasps with single view in real time. DexGanGrasp comprises a Conditional Generative Ad…
FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference
Qian Feng, Jianxiang Feng, Zhaopeng Chen +2
Synthesizing diverse, uncertainty-aware grasps for multi-fingered hands from partial observations remains a critical challenge in robot learning. Prior generative methods struggle…
Language-Guided Object-Centric Diffusion Policy for Generalizable and Collision-Aware Robotic Manipulation
Hang Li, Qian Feng, Zhi Zheng +3
Learning from demonstrations faces challenges in generalizing beyond the training data and often lacks collision awareness. This paper introduces Lan-o3dp, a language-guided object…
Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners
Zhi Zheng, Qian Feng, Hang Li +2
Recently, Large Language Models (LLMs) have witnessed remarkable performance as zero-shot task planners for robotic manipulation tasks. However, the open-loop nature of previous wo…