2 papers
cs.CV2026
Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift
Lixian Chen, Yanhui Chen, Mingxuan Huang +2
Vision--language models can face asymmetric visual and textual shifts at deployment. These shifts expose a multimodal failure mode in which an unreliable branch remains overconfide…
cs.CV2026
TransSplat: Unbalanced Semantic Transport for Language-Driven 3DGS Editing
Yanhui Chen, Jiahong Li, Jingchao Wang +3
Language-driven 3D Gaussian Splatting (3DGS) editing provides a more convenient approach for modifying complex scenes in VR/AR. Standard pipelines typically adopt a two-stage strat…