Jiacheng Sun

6

Papers

31

Total Citations

Papers (6)

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

NeurIPS 2025arXiv

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

PolarNeXt: Rethink Instance Segmentation with Polar Representation

Towards Transformer-Based Aligned Generation with Self-Coherence Guidance

Adding Additional Control to One-Step Diffusion with Joint Distribution Matching

Masked Diffusion Models as Energy Minimization