Shen, Chunhua

SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories

Zhu, M., Tian, Y., Chen, H., Zhou, C., Guo, Q., Liu, Y., Yang, M., & Shen, C. (2025) · arXiv

Multimodal Machine Learning ApplicationsAdvanced Neural Network Applications

Cited by 5

ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning

Zhu, M., Zhong, H., Zhao, C., Du, Z., Liu, M., Huang, Z., Li, A., Chen, H., Zou, C., Chen, J., et al. (2025) · arXiv

Multimodal Machine Learning ApplicationsRobot Manipulation and Learning

Cited by 0