Kyoto College of Graduate Studies for Informatics

From Instruction to Inheritance: Scaling Robot Learning Through Knowledge Circulation

Robot learning, particularly through vision–language–action (VLA) models, has rapidly improved the ability of robots to execute instructed tasks. However, the current mainstream paradigm of robot learning largely depends on one‐way instruction from humans to robots, lacking a cyc...

Emergence of Goal‐Directed Behaviors via Active Inference With Self‐Prior

ABSTRACT Infants often exhibit goal‐directed behaviors, such as reaching for a sensory stimulus, even when no external reward criterion is provided. These intrinsically motivated behaviors facilitate spontaneous exploration and learning of the body and environment during early de...

Development of a python interface for a framework of cross-reference solar-terrestrial physics simulation

Cross-reference simulation combines multiple simulation codes when one code requires data produced by another. To provide an efficient and convenient solution for cross-reference Solar-Terrestrial Physics (STP) simulation, a framework called Code-To-Code Adapter (CoToCoA) Library...

The strongly stable roommates problem and linear programming

The stable roommates problem is a non-bipartite version of the stable matching problem in a bipartite graph. In this paper, we consider the stable roommates problem with ties. In particular, we focus on strong stability, which is one of the main stability concepts in the stable r...