Yujun Shi
11 papers · 2021–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (24) 🐣 Hot Topic Early Bird 🗃️ Keyword Collector (61)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Deep Learning
(10)
Machine Learning
(6)
Computer Vision
(5)
Learning Types · Machine Learning
(5)
Learning Types · Deep Learning
(5)
Models
(5)
Artificial Intelligence
(3)
Architectures
(3)
Generation
(3)
Processing
(3)
Core Methods
(2)
Learning Paradigms
(2)
Application Areas
(1)
Core AI · Computer Vision
(1)
Core AI · Artificial Intelligence
(1)
Keywords
representation learning
(3)
knowledge distillation
(2)
text-to-video generation
(2)
class-incremental learning
(2)
continual learning
(2)
image classification
(2)
latent optimization
(2)
vision transformer
(2)
conditional generation
(1)
few-shot learning
(1)
contrastive learning
(1)
federated learning
(1)
information preservation
(1)
feature learning
(1)
diffusion model
(1)
semantic segmentation
(1)
neural architecture
(1)
information gain
(1)
image editing
(1)
catastrophic forgetting
(1)
Papers
Identity-Preserving Text-to-Video Generation by Frequency Decomposition
CVPR 2025
LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos
ICML 2025
ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
NeurIPS 2024
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
CVPR 2024
Learning With Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning
CVPR 2023
Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
NeurIPS 2023
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
ICLR 2023
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
CVPR 2022
All Tokens Matter: Token Labeling for Training Better Vision Transformers
NeurIPS 2021
Continual Learning via Bit-Level Information Preserving
CVPR 2021
Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet
ICCV 2021