5 papers
Spectral-Structured Diffusion for Single-Image Rain Removal
Yucheng Xing, Xin Wang
Rain streaks manifest as directional and frequency-concentrated structures that overlap across multiple scales, making single-image rain removal particularly challenging. While dif…
N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
Yucheng Xing, Xin Wang
Long-horizon wildfire risk forecasting requires generating probabilistic spatial fields under sparse event supervision while maintaining computational efficiency across multiple pr…
Input-Adaptive Generative Dynamics in Diffusion Models
Yucheng Xing, Xiaodong Liu, Xin Wang
Diffusion models typically generate data through a fixed denoising trajectory that is shared across all samples. However, generation targets can differ in complexity, suggesting th…
Puppet-CNN: Continuous Parameter Dynamics for Input-Adaptive Convolutional Networks
Yucheng Xing, Xin Wang
Modern convolutional neural networks (CNNs) organize computation as a discrete stack of layers whose parameters are independently stored and learned, with the number of layers fixe…
Map-Free Trajectory Prediction with Map Distillation and Hierarchical Encoding
Xiaodong Liu, Yucheng Xing, Xin Wang
Reliable motion forecasting of surrounding agents is essential for ensuring the safe operation of autonomous vehicles. Many existing trajectory prediction methods rely heavily on h…