3 papers
cs.CV2025
SyncMapV2: Robust and Adaptive Unsupervised Segmentation
Heng Zhang, Zikang Wan, Danilo Vasconcellos Vargas
Human vision excels at segmenting visual cues without the need for explicit training, and it remains remarkably robust even as noise severity increases. In contrast, existing AI al…
cs.CL2025
Scaling Laws in Scientific Discovery with AI and Robot Scientists
Pengsong Zhang, Heng Zhang, Huazhe Xu +7
Scientific discovery is poised for rapid advancement through advanced robotics and artificial intelligence. Current scientific practices face substantial limitations as manual expe…
cs.CV2023
Decompose Semantic Shifts for Composed Image Retrieval
Xingyu Yang, Daqing Liu, Heng Zhang +3
Composed image retrieval is a type of image retrieval task where the user provides a reference image as a starting point and specifies a text on how to shift from the starting poin…