14 papers
WorldString: Actionable World Representation
Kunqi Xu, Jitao Li, Jianglong Ye +4
Inspired by the emergent behaviors in large language models that generalized human intelligence, the research community is pursuing similar emergent capabilities within world model…
Quantitative Video World Model Evaluation for Geometric-Consistency
Jiaxin Wu, Yihao Pi, Yinling Zhang +2
Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Mos…
Long-Horizon Manipulation via Trace-Conditioned VLA Planning
Isabella Liu, An-Chieh Cheng, Rui Yan +7
Long-horizon manipulation remains challenging for vision-language-action (VLA) policies: real tasks are multi-step, progress-dependent, and brittle to compounding execution errors.…
Cross-Hand Latent Representation for Vision-Language-Action Models
Guangqi Jiang, Yutong Liang, Jianglong Ye +6
Dexterous manipulation is essential for real-world robot autonomy, mirroring the central role of human hand coordination in daily activity. Humans rely on rich multimodal perceptio…
From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands
Jianglong Ye, Lai Wei, Guangqi Jiang +3
Human grasps can be roughly categorized into two types: power grasps and precision grasps. Precision grasping enables tool use and is believed to have influenced human evolution. T…
GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation
Guangqi Jiang, Haoran Chang, Ri-Zhao Qiu +6
This paper presents GSWorld, a robust, photo-realistic simulator for robotics manipulation that combines 3D Gaussian Splatting with physics engines. Our framework advocates "closin…