collaborators

5 papers

cs.CV2026

SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching

Zong-Wei Hong, Jinglun Li, Shen Zhang +3

Denoising diffusion transformers achieve strong generation quality but converge slowly during training. Regularizing their internal representations has emerged as an effective acce…

cs.CV2026

The Velocity Deficit: Initial Energy Injection for Flow Matching

Linze Li, Zong-Wei Hong, Shen Zhang +4

While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity Deficit. We show that the M…

cs.CV2026

VeCoR -- Velocity Contrastive Regularization for Flow Matching

Zong-Wei Hong, Jing-lun Li, Lin-Ze Li +2

Flow Matching (FM) has recently emerged as a principled and efficient alternative to diffusion models. Standard FM encourages the learned velocity field to follow a target directio…

cs.CV2025

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

Ge Wu, Shen Zhang, Ruijing Shi +9

REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models, through alignment betwee…

cs.CV2025

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

Shen Zhang, Siyuan Liang, Yaning Tan +9

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE),…