4 papers
RopeFormer: Cross-Trial Adaptation from Interaction History for Dynamic Rope Manipulation
Menglin Wu, Kaixiang Yao, Shangbo Luan +2
Dynamic rope manipulation is highly sensitive to unknown object dynamics: the same robot motion can produce substantially different responses across ropes, while explicitly identif…
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
Kaixiang Yao, Xu Wang, Miao Pan +7
Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local stat…
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
Xu Wang, Kaixiang Yao, Miao Pan +4
Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks are grounded in continuous vi…
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Wangjie Gan, Miao Pan, Linbo Xi +4
Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with rob…