Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Second Order Drifting Models
Drake Brown, Yuhao Huang, Shih-Hsin Wang +1
Drifting models are a recent class of one-step generative models that evolve the model distribution during training using a predefined sample-based drift field. Although they avoid…
cs.LG2026
Improving Flow Matching by Aligning Flow Divergence
Yuhao Huang, Taos Transue, Shih-Hsin Wang +3
Conditional flow matching (CFM) stands out as an efficient, simulation-free approach for training flow-based generative models, achieving remarkable performance for data generation…
cs.LG2026
RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
Yuhao Huang, Shih-Hsin Wang, Andrea L. Bertozzi +1
Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this…