Xiaojuan Qi
21 papers · 5 citations
Most-cited papers
- Stratified Transformer For 3D Point Cloud Segmentation2022 · 480 citations
- Manigan: Text-guided Image Manipulation2019 · 227 citations
- Regionplc: Regional Point-language Contrastive Learning For Open-world 3D Scene Understanding2023 · 60 citations
- Groma: Localized Visual Tokenization For Grounding Multimodal Large Language Models2024 · 40 citations
- Eschernet: A Generative Model For Scalable View Synthesis2024 · 30 citations
- Noteit: A System Converting Instructional Videos To Interactable Notes Through Multimodal Video Understanding2025 · 3 citations
- Seqtex: Generate Mesh Textures In Video Sequence2025 · 1 citations
- Equipping Vision Foundation Model With Mixture Of Experts For Out-of-distribution Detection2025 · 1 citations
- Mindomni: Unleashing Reasoning Generation In Vision Language Models With RGPO2025
- Vision Foundation Models As Effective Visual Tokenizers For Autoregressive Image Generation2025
Topics