Yujun Shi

8

Papers

308

Total Citations

Papers (8)

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

Continual Learning via Bit-Level Information Preserving

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

Learning With Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning

Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet

All Tokens Matter: Token Labeling for Training Better Vision Transformers

NeurIPS 2021arXiv

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

NeurIPS 2023arXiv