5 papers
Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation
Yungeng Liu, Xuanzi Fang, Yuge Zhang +3
Kolmogorov--Arnold Networks (KANs) introduce explicit functional representations by parameterizing each network edge as a learnable univariate function. However, existing KAN-based…
Decoupling Language Guidance from Backbones for Text-Guided Medical Segmentation
Yungeng Liu, Xuanzi Fang, Haijin Zeng +2
Text-guided medical image segmentation leverages clinical semantics to improve lesion delineation, yet many existing models bind cross-modal fusion, supervision, and decoder design…
Agentic Flow Steering and Parallel Rollout Search for Spatially Grounded Text-to-Image Generation
Ping Chen, Daoxuan Zhang, Xiangming Wang +3
Precise Text-to-Image (T2I) generation has achieved great success but is hindered by the limited relational reasoning of static text encoders and the error accumulation in open-loo…
HSI-VAR: Rethinking Hyperspectral Restoration through Spatial-Spectral Visual Autoregression
Xiangming Wang, Benteng Sun, Yungeng Liu +4
Hyperspectral images (HSIs) capture richer spatial-spectral information beyond RGB, yet real-world HSIs often suffer from a composite mix of degradations, such as noise, blur, and…
Vision-Language Controlled Deep Unfolding for Joint Medical Image Restoration and Segmentation
Ping Chen, Zicheng Huang, Xiangming Wang +4
We propose VL-DUN, a principled framework for joint All-in-One Medical Image Restoration and Segmentation (AiOMIRS) that bridges the gap between low-level signal recovery and high-…