← authors · overview

• Shunted Self-attention Via Multi-scale Token Aggregation
  2021 · 310 citations
• Mambaout: Do We Really Need Mamba For Vision?
  2024 · 243 citations
• Mambaout: Do We Really Need Mamba For Vision?
  2024 · 128 citations
• Graphadapter: Tuning Vision-language Models With Dual Knowledge Graph
  2023 · 115 citations
• Adapting Visual-language Models For Generalizable Anomaly Detection In Medical Images
  2024 · 111 citations
• Diffusion Model As Representation Learner
  2023 · 100 citations
• Sg-former: Self-guided Transformer With Evolving Token Reallocation
  2023 · 70 citations
• Sg-former: Self-guided Transformer With Evolving Token Reallocation
  2023 · 59 citations
• Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
  2023 · 41 citations
• Gamba: Marry Gaussian Splatting With Mamba For Single View 3D Reconstruction
  2024 · 19 citations
• C4D: 4D Made From 3D Through Dual Correspondences
  2025 · 1 citations
• Test3r: Learning To Reconstruct 3D At Test Time
  2025
• Diversity-guided MLP Reduction For Efficient Large Vision Transformers
  2025
• In-video Instructions: Visual Signals As Generative Control
  2025
• Reasonmap: Towards Fine-grained Visual Reasoning From Transit Maps
  2025