5 papers
Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
Xinyi Li, Zaishuo Xia, Chenjie Hao +1
World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursivel…
Bridging Semantics and Physical Execution: A Neuro-Symbolic Framework for Multi-Pair Robotic Assembly
Xinyi Li, Aiguo Song, Linhu Wei +1
Multi-pair robotic assembly in unstructured environments faces spatial interference and contact uncertainties. Existing paradigms fail to bridge cognitive decision-making and physi…
SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments
Xinyi Li, Zaishuo Xia, Weyl Lu +2
Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying rules that govern envi…
GUIDES: Guidance Using Instructor-Distilled Embeddings for Pre-trained Robot Policy Enhancement
Minquan Gao, Xinyi Li, Qing Yan +4
Pre-trained robot policies serve as the foundation of many validated robotic systems, which encapsulate extensive embodied knowledge. However, they often lack the semantic awarenes…
Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
Zaishuo Xia, Yukuan Lu, Xinyi Li +2
A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and i…