4 citations · 7 across the 7 of their papers we have counts for
7 papers
Topology-Aware Parameter-Efficient Adaptation for Cross-Dataset Retinal Vessel Segmentation
Yongsong Huang, Tomo Miyazaki, Kai Xu +3
Retinal vessel segmentation in multi-domain deployment requires a source model to adapt to domains that differ in imaging conditions and annotation conventions. Conventional parame…
AdaPower: Specializing World Foundation Models for Predictive Manipulation
Yuhang Huang, Shilong Zou, Jiazhao Zhang +3
World Foundation Models (WFMs) offer remarkable visual dynamics simulation capabilities, yet their application to precise robotic control remains limited by the gap between generat…
CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation
Shilong Zou, Yuhang Huang, Renjiao Yi +2
We introduce a diffusion-based cross-domain image translator in the absence of paired training data. Unlike GAN-based methods, our approach integrates diffusion models to learn the…
LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation
Yuhang Huang, Jiazhao Zhang, Shilong Zou +3
Predictive manipulation has recently gained considerable attention in the Embodied AI community due to its potential to improve robot policy performance by leveraging predicted sta…
DISCO: Efficient Diffusion Solver for Large-Scale Combinatorial Optimization Problems
Hang Zhao, Kexiong Yu, Yuhang Huang +3
Combinatorial Optimization (CO) problems are fundamentally important in numerous real-world applications across diverse industries, characterized by entailing enormous solution spa…
Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fields
Yuhang Huang, SHilong Zou, Xinwang Liu +1
This paper presents a novel latent 3D diffusion model for the generation of neural voxel fields, aiming to achieve accurate part-aware structures. Compared to existing methods, the…
DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection
Yunfan Ye, Kai Xu, Yuhang Huang +2
Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent…