Published in Arxiv, 2025
In GenDexHand, we propose a generative pipeline for dexterous hand tasks that combines LLM/VLM refinement, motion planning, DoF constraints, and subtask decomposition to generate scalable, high-quality trajectory data.
Download here
Published in Arxiv, 2024
In EvalTask, we propose a novel framework for evaluating generative robotic simulations from various aspects.
Download here
Published in Arxiv, 2023
We present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation.
Download here
Published in NeurIPS, 2023, 2023
This paper is how to use both vision and language information help to solve soft body manipulation tasks. Also, we introduce non-expert into setting up dataset by UI-system and large language model. Paper site
Download here