← authors · overview

• Vision Transformer With Deformable Attention
  2022 · 801 citations
• GSVA: Generalized Segmentation Via Multimodal Large Language Models
  2023 · 69 citations
• Fine-grained Few Shot Learning With Foreground Object Transformation
  2021 · 27 citations
• Latency-aware Unified Dynamic Networks For Efficient Image Recognition
  2023 · 21 citations
• Demystify Mamba In Vision: A Linear Attention Perspective
  2024 · 13 citations