Ruihua Song

Papers

Total Citations

H-Index

About

Ruihua Song is a researcher working at the cutting edge of robotics and artificial intelligence, with a focus on generalizable robotic manipulation and multi-task policy learning. His work addresses one of the most pressing challenges in modern robotics: enabling robots to perform reliably and flexibly in real-world environments without requiring prohibitively large and costly datasets. In his notable 2025 paper, "Transferring Foundation Models for Generalizable Robotic Manipulation," Song explores how foundation models — powerful pretrained systems developed for vision and language — can be leveraged to improve the generalization capabilities of robotic systems, reducing dependence on expensive large-scale robotic data collection. This work has already attracted 6 citations since its publication, signaling early recognition from the research community. His 2024 contribution, "RoLD: Robot Latent Diffusion for Multi-task Policy Modeling," further demonstrates his interest in applying advanced generative modeling techniques, specifically diffusion models, to enable robots to master multiple tasks through unified policy frameworks. Together, these works position Song as an emerging voice in the robotics community, contributing innovative solutions that bridge foundation model research with practical robotic deployment.