PPaperPicks

Hangjie Yuan

22 papers at tracked venues · 21 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Adapt Before Continual Learning
  2. Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
  3. MCIE: Multimodal LLM-Driven Complex Instruction Image Editing with Spatial Guidance
  4. MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
  5. OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
  6. AeroGTO: An Efficient Graph-Transformer Operator for Learning Large-Scale Aerodynamics of 3D Vehicle Geometries
  7. DreamRelation: Relation-Centric Video Customization
  8. FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
  9. FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
  10. Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
  11. SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images
  12. UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback
  13. VideoMAR: Autoregressive Video Generation with Continuous Tokens
  14. ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
  15. A Recipe for Scaling up Text-to-Video Generation with Text-free Videos
  16. Dream Video: Composing Your Dream Videos with Customized Subject and Motion
  17. EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
  18. InstructVideo: Instructing Video Diffusion Models with Human Feedback
    CVPR 2024 · Hangjie Yuan
  19. LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
  20. Make Continual Learning Stronger via C-Flat
  21. PAPM: A Physics-aware Proxy Model for Process Systems
  22. Revisiting Neural Networks for Continual Learning: An Architectural Perspective