PPaperPicks

Songhua Liu

18 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. FreLay: Frequency-aware Energy Function for Training-free Layout-to-Image Generation
  2. CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
    NeurIPS 2025 · Songhua Liu
  3. Control and Realism: Best of Both Worlds in Layout-to-Image without Training
  4. Diffusion Model is Effectively Its Own Teacher
  5. Hash3D: Training-free Acceleration for 3D Generation
  6. Heavy Labels Out! Dataset Distillation with Label Space Lightening
  7. Image Editing As Programs with Diffusion Models
  8. OminiControl: Minimal and Universal Control for Diffusion Transformer
  9. Open-World Authorship Attribution
  10. POSTA: A Go-to Framework for Customized Artistic Poster Generation
  11. Ultra-Resolution Adaptation with Ease
  12. UniversalBooth: Model-Agnostic Personalized Text-To-Image Generation
    ICCV 2025 · Songhua Liu
  13. Distilled Datamodel with Reverse Gradient Matching
  14. MindBridge: A Cross-Subject Brain Decoding Framework
  15. Mutual-Modality Adversarial Attack with Semantic Perturbation
  16. One-shot Federated Learning via Synthetic Distiller-Distillate Communication
  17. StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
    ICML 2024 · Songhua Liu
  18. Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching