3 papers
cs.CV2026
NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation
Yu Zeng, Charles Ochoa, Mingyuan Zhou +3
Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image genera…
cs.LG2025
Distilled Protein Backbone Generation
Liyang Xie, Haoran Zhang, Zhendong Wang +2
Diffusion- and flow-based generative models have recently demonstrated strong performance in protein backbone generation tasks, offering unprecedented capabilities for de novo prot…
cs.LG2025
Controllable diffusion-based generation for multi-channel biological data
Haoran Zhang, Mingyuan Zhou, Wesley Tansey
Spatial profiling technologies in biology, such as imaging mass cytometry (IMC) and spatial transcriptomics (ST), generate high-dimensional, multi-channel data with strong spatial…