← authors · overview

• Self-positioning Point-based Transformer for Point Cloud Understanding
  2023 · 116 citations
• MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
  2023 · 66 citations
• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
  2020 · 41 citations
• ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification
  2019 · 18 citations
• EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
  2023 · 15 citations
• SageMix: Saliency-Guided Mixup for Point Clouds
  2022 · 13 citations
• Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
  2022 · 3 citations
• PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
  2022 · 1 citations
• Efficient Universal Perception Encoder
  2026
• VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
  2026
• EdgeTAM: On-Device Track Anything Model
  2025
• SqueezeSAM: User friendly mobile interactive segmentation
  2023