📖 Publications

FSAG: Enhancing Human-to-Dexterous-Hand Finger-Specific Affordance Grounding via Diffusion Models

• We propose a data-efficient framework, which is designed to bypass robot grasp data collection by exploiting the rich, object-centric semantic priors latent in pretrained generative diffusion models.

SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks

• We propose SAGE, a novel framework for Scene Graph-Aware Guidance and Execution in Long-Horizon Manipulation Tasks

LLGS: Unsupervised Gaussian Splatting for Image Enhancement and Reconstruction in Pure Dark Environment

• We propose an unsupervised multi-view stereoscopic system based on Gaussian Splatting, called Low-Light Gaussian Splatting.

Meta-Scoop: A Coarse-to-Precise Policy Learning Framework for Precision Scooping Across Task Variations

• We have proposed a framework that progresses from rough to precise, enabling precise extraction operations in various task variations.

Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation

• We introduce the Triplet-to-Track System (TTS), a closed-loop long-horizon imitation learning system that uses human videos to reduce reliance on robot-collected data.