2 papers
cs.RO2025
Few-Shot Vision-Language Action-Incremental Policy Learning
Mingchen Song, Xiang Deng, Guoqiang Zhong +5
Recently, Transformer-based robotic manipulation methods utilize multi-view spatial representations and language instructions to learn robot motion trajectories by leveraging numer…
cs.CV2025
Dynamic Degradation Decomposition Network for All-in-One Image Restoration
Huiqiang Wang, Mingchen Song, Guoqiang Zhong
Currently, restoring clean images from a variety of degradation types using a single model is still a challenging task. Existing all-in-one image restoration approaches struggle wi…