Songhua Liu
34 papers · 2021–2026 · 7 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (54) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π¬
Deep Specialist
(10)
π€
Dynamic Duo
(29)
π§¬
Topic Evolution
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
ποΈ
Keyword Collector
(135)
π
Century Club Β· Bronze
Top co-authors
Research topics
Deep Learning
(22)
Machine Learning
(21)
Computer Vision
(14)
Application Areas
(13)
Models
(13)
Generation
(12)
Artificial Intelligence
(11)
Core AI
(7)
Architectures
(6)
Learning Types Β· Deep Learning
(6)
Learning Types Β· Machine Learning
(6)
Core Methods
(5)
Learning Paradigms
(5)
Optimization & Theory Β· Machine Learning
(3)
Optimization & Theory Β· Deep Learning
(3)
Keywords
diffusion model
(7)
knowledge distillation
(6)
image generation
(5)
neural network
(4)
synthetic data
(4)
dataset distillation
(4)
generative model
(3)
transfer learning
(3)
diffusion transformer
(3)
few-shot learning
(2)
synthetic dataset
(2)
image editing
(2)
model compression
(2)
attention mechanism
(2)
large language model
(2)
domain generalization
(1)
self-attention mechanism
(1)
langevin dynamics
(1)
neural decoding
(1)
federated learning
(1)
Papers
EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
CVPR 2026
FreLay: Frequency-aware Energy Function for Training-free Layout-to-Image Generation
AAAI 2026
Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers
CVPR 2026
MultiAnimate: Pose-Guided Image Animation Made Extensible
CVPR 2026
RunawayEvil: Jailbreaking the Image-to-Video Generative Models
CVPR 2026
SpotEdit: Selective Region Editing in Diffusion Transformers
CVPR 2026
Control and Realism: Best of Both Worlds in Layout-to-Image without Training
ICML 2025
Diffusion Model is Effectively Its Own Teacher
CVPR 2025
Hash3D: Training-free Acceleration for 3D Generation
CVPR 2025
Heavy Labels Out! Dataset Distillation with Label Space Lightening
ICCV 2025
OminiControl: Minimal and Universal Control for Diffusion Transformer
ICCV 2025
Open-World Authorship Attribution
ACL 2025
POSTA: A Go-to Framework for Customized Artistic Poster Generation
CVPR 2025
Ultra-Resolution Adaptation with Ease
ICML 2025
UniversalBooth: Model-Agnostic Personalized Text-to-Image Generation
ICCV 2025
Distilled Datamodel with Reverse Gradient Matching
CVPR 2024
MindBridge: A Cross-Subject Brain Decoding Framework
CVPR 2024
Mutual-Modality Adversarial Attack with Semantic Perturbation
AAAI 2024
One-shot Federated Learning via Synthetic Distiller-Distillate Communication
NeurIPS 2024
StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
ICML 2024
Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching
ECCV 2024
Distribution Shift Inversion for Out-of-Distribution Prediction
CVPR 2023
Few-Shot Dataset Distillation via Translative Pre-Training
ICCV 2023
Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
CVPR 2023
MGDD: A Meta Generator for Fast Dataset Distillation
NeurIPS 2023
Partial Network Cloning
CVPR 2023
SG-Former: Self-guided Transformer with Evolving Token Reallocation
ICCV 2023
Slimmable Dataset Condensation
CVPR 2023
Dataset Distillation via Factorization
NeurIPS 2022
Deep Model Reassembly
NeurIPS 2022
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation
ECCV 2022
Learning with Recoverable Forgetting
ECCV 2022
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
ICCV 2021
Paint Transformer: Feed Forward Neural Painting With Stroke Prediction
ICCV 2021