← authors · overview

• Robust Attentional Aggregation Of Deep Feature Sets For Multi-view 3D Reconstruction
  2018 · 113 citations
• PIG: Prompt Images Guidance For Night-time Scene Parsing
  2024 · 9 citations
• Panogen++: Domain-adapted Text-guided Panoramic Environment Generation For Vision-and-language Navigation
  2025 · 8 citations
• No Token Left Behind: Efficient Vision Transformer Via Dynamic Token Idling
  2023 · 7 citations
• Object Detection Difficulty: Suppressing Over-aggregation For Faster And Better Video Object Detection
  2023 · 4 citations
• Distributed Zero-shot Learning For Visual Recognition
  2025 · 2 citations
• Flowram: Grounding Flow Matching Policy With Region-aware Mamba Framework For Robotic Manipulation
  2025 · 1 citations
• Repavit: Scalable Vision Transformer Acceleration Via Structural Reparameterization On Feedforward Network Layers
  2025
• GALA: Guided Attention With Language Alignment For Open Vocabulary Gaussian Splatting
  2025
• NAS-GS: Noise-aware Sonar Gaussian Splatting
  2026