activity
20242026
collaborators

12 papers

cs.CV2026

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance

Yujie Wei, Shiwei Zhang, Hangjie Yuan +8

Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language mode…

cs.CV2025

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

Haonan Qiu, Shiwei Zhang, Yujie Wei +5

Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resou…

cs.CV2025

DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing

Lingling Cai, Kang Zhao, Hangjie Yuan +3

The advent of Video Diffusion Transformers (Video DiTs) marks a milestone in video generation. However, directly applying existing video editing methods to Video DiTs often incurs…

cs.CV2025

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

Tao Feng, Wei Li, Didi Zhu +4

Backpropagation provides a generalized configuration for overcoming catastrophic forgetting. Optimizers such as SGD and Adam are commonly used for weight updates in continual learn…

cs.CV2025

Taming Consistency Distillation for Accelerated Human Image Animation

Xiang Wang, Shiwei Zhang, Hangjie Yuan +5

Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs…

cs.CV2025

DreamRelation: Relation-Centric Video Customization

Yujie Wei, Shiwei Zhang, Hangjie Yuan +8

Relational video customization refers to the creation of personalized videos that depict user-specified relations between two subjects, a crucial task for comprehending real-world…