Research

Research Interests

Ongoing Projects

ROSWORLD: Robotic Computer Use for OSWorld Tasks

Caoyuan Ma*, Wendi Liu*, Wenqi Shao, Yinqiang Zheng
* Equal contribution (co-first authors).

A long-term benchmark connecting Isaac Sim robots with a real virtual machine. Models operate a keyboard and mouse through robotic actions to complete OSWorld tasks, with ongoing task and leaderboard updates.

Project released October 12, 2026 (AoE). Full research code, assets, and an arXiv report are planned for release by the end of October 2026.

Publications

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law

SAI Labs, Y Bao, etc. Caoyuan Ma
arXiv, 2025

SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning

Caoyuan Ma, Liuwenpu, Weichu Xie, Tian Gu, Shilei Zhao, Lingxi Min, Shuai Dong, Yuqi Xu, Ji Zhao, Ziyue Wang, Wenzheng Chang, Taiqiang Wu, Yongfu Zhu, Wenqi Shao, Yinqiang Zheng
arXiv, 2026

SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models

Caoyuan Ma*, Tian Gu*, Liuwenpu, Weichu Xie, Shuai Dong, Yuqi Xu, Ji Zhao, Ziyue Wang, Wenzheng Chang, Taiqiang Wu, Yongfu Zhu, Wenqi Shao, Zheng Wang, Yinqiang Zheng
arXiv, 2026

TAAT: Think and Act from Arbitrary Texts

Runqi Wang*, Caoyuan Ma*, Guopeng Li*, Zheng Wang
International Conference on Computer Vision (ICCV), 2025

Subjective Camera: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion

Haoyang Chen*, Dongfang Sun*, Caoyuan Ma*, Shiqin Wang, Kewei Zhang, Zheng Wang, Zhixiang Wang
International Conference on Computer Vision (ICCV), 2025

Leader and Follower: Interactive Motion Generation under Trajectory Constraints

Runqi Wang*, Caoyuan Ma*, Jian Zhao, Hanrui Xu, Dongfang Sun, Haoyang Chen, Lin Xiong, Zheng Wang, Xuelong Li
ACM International Conference on Multimedia (ACM MM), 2024

Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfer

Zhimin Zhang*, Bi'an Du*, Caoyuan Ma, Zheng Wang, Wei Hu
ACM International Conference on Multimedia (ACM MM), 2025

Causal deciphering and inpainting in spatio-temporal dynamics via diffusion model

Yifan Duan, Jian Zhao, Junyuan Mao, Hao Wu, Jingyu Xu, Caoyuan Ma, Kai Wang, Kun Wang, Xuelong Li
Neural Information Processing Systems (NeurIPS), 2024

HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses

Caoyuan Ma, Yu-Lun Liu, Zhixiang Wang, Wu Liu, Xinchen Liu, Zheng Wang
Computer Vision and Pattern Recognition (CVPR), 2024

Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information

Fengji Zhang, Xiao Yu, Jacky Keung, Fuyang Li, Zhiwen Xie, Zhen Yang, Caoyuan Ma, Zhimin Zhang
Information and Software Technology, 2022