Lune

Profiles2022-2024

Renrui Zhang

Shanghai Artificial Intelligence Laboratory

14Papers
0Last author
16Unique co-authors
7First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers14

  1. Personalize Segment Anything Model with One ShotAuthor 1 of 11ICLR 2024 · 333 citations
  2. LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized AttentionAuthor 1 of 9ICLR 2024 · 174 citations
  3. SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language ModelsAuthor 2 of 19ICML 2024 · 149 citations
  4. Referred by Multi-Modality: A Unified Temporal Transformer for Video Object SegmentationAuthor 2 of 10AAAI 2024 · 67 citations
  5. No Time to Train: Empowering Non-Parametric Networks for Few-Shot 3D Scene SegmentationAuthor 2 of 9CVPR 2024 · 14 citations
  6. PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world LearningAuthor 2 of 8ICCV 2023 · 248 citations
  7. CALIP: Zero-Shot Enhancement of CLIP with Parameter-Free AttentionAuthor 2 of 7AAAI 2023 · 182 citations
  8. MonoDETR: Depth-guided Transformer for Monocular 3D Object DetectionAuthor 1 of 11ICCV 2023 · 175 citations
  9. Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior RefinementAuthor 2 of 7ICCV 2023 · 121 citations
  10. Learning 3D Representations from 2D Pre-Trained Models via Image-to-Point Masked AutoencodersAuthor 1 of 5CVPR 2023
  11. PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object DetectionAuthor 3 of 7CVPR 2023
  12. Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot LearnersAuthor 1 of 8CVPR 2023
  13. Starting from Non-Parametric Networks for 3D Point Cloud AnalysisAuthor 1 of 7CVPR 2023
  14. Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingAuthor 1 of 8NeurIPS 2022 · 445 citations
Dusk over the sea between two cliffs drawn in fine vertical lines