3 papers
cs.RO2026
Task-Prototype Guided Flow Matching for Few-Shot Generalization in Vision-Language Robot Manipulation
Yizhao Wang, Guantao Zhang, Jingbo Wang
Vision-language robot manipulation policies can follow semantic instructions, but adapting them to a new procedure from only a few demonstrations remains difficult because language…
cs.CV2026
Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flows
Yizhao Wang, Jingbo Wang, Guantao Zhang
Class-guided 3D object generation is important for intelligent content creation, virtual environments, and digital asset design. Although 3D Gaussian Splatting (3DGS) offers an exp…
cs.CV2026
Beyond Similarity Matching: Structured Reasoning for Open-Vocabulary Referring Segmentation in 3DGS
Yizhao Wang, Xinfa Wang, Jingbo Wang +4
Open-vocabulary referring segmentation in 3D Gaussian Splatting (3DGS) requires a neural model to select Gaussian primitives according to free-form language expressions. Existing 3…