Profiles2021-2025
Peng Gao
Shanghai Artificial Intelligence Laboratory
16Papers
8Last author
25Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers16
- Spatial Preference Rewarding for MLLMs Spatial UnderstandingAuthor 2 of 6ICCV 2025 · 3 citations
- Fontanimate: High Quality Few-Shot Font Generation Via Animating Font Transfer ProcessAuthor 8 of 8ICCV 2025 · 1 citation
- Personalize Segment Anything Model with One ShotAuthor 9 of 11ICLR 2024 · 333 citations
- LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized AttentionAuthor 8 of 9ICLR 2024 · 174 citations
- SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language ModelsAuthor 19 of 19ICML 2024 · 149 citations
- Referred by Multi-Modality: A Unified Temporal Transformer for Video Object SegmentationAuthor 10 of 10AAAI 2024 · 67 citations
- No Time to Train: Empowering Non-Parametric Networks for Few-Shot 3D Scene SegmentationAuthor 9 of 9CVPR 2024 · 14 citations
- Masked AutoDecoder is Effective Multi-Task Vision GeneralistAuthor 3 of 6CVPR 2024
- PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world LearningAuthor 8 of 8ICCV 2023 · 248 citations
- MonoDETR: Depth-guided Transformer for Monocular 3D Object DetectionAuthor 10 of 11ICCV 2023 · 175 citations
- Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior RefinementAuthor 7 of 7ICCV 2023 · 121 citations
- Learning 3D Representations from 2D Pre-Trained Models via Image-to-Point Masked AutoencodersAuthor 4 of 5CVPR 2023
- Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot LearnersAuthor 8 of 8CVPR 2023
- Starting from Non-Parametric Networks for 3D Point Cloud AnalysisAuthor 4 of 7CVPR 2023
- Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingAuthor 8 of 8NeurIPS 2022 · 445 citations
- Dense Contrastive Visual-Linguistic PretrainingAuthor 4 of 9ACM MM 2021 · 12 citations
