4 papers
Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
Jiaxin Bai, Jiaxuan Xiong
Joint-Embedding Predictive Architectures (JEPAs) learn world models by predicting in representation space rather than reconstructing pixels, making them a natural backbone for late…
VisualPatchWorld: Code World Models as Latent Structured Representations for Planning
Jiaxin Bai, Jiaxuan Xiong
Different research lines use the term world model in different ways, yet they share a common aim: to capture how the world evolves under action in a form that supports perception,…
PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
Jiaxin Bai, Yue Guo, Yifei Dong +13
World models for interactive text agents must typically be learned from observation-action trajectories alone. Specifically, the environment returns text observations after each ac…
NGDBench: Towards Neural Graph Data Management
Yufei Li, Yisen Gao, Jiaxuan Xiong +6
Data critical to real-world decision-making is increasingly found within organizations. Such data is heterogeneous, constantly evolving, and only imperfectly captured. However, cur…