Lune

Profiles2020-2026

Xiaojuan Qi

The University of Hong Kong

42Papers
25Last author
74Unique co-authors
0First author
0Solo

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

Recent papers42

  1. Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language ModelsAuthor 7 of 7CVPR 2026 · 10 citations
  2. Stable Velocity: A Variance Perspective on Flow MatchingAuthor 7 of 8ICML 2026 · 6 citations
  3. Stabilizing Streaming Video Geometry via Dynamic Feature NormalizationAuthor 8 of 10CVPR 2026 · 3 citations
  4. Absorbing Quantization Error by Deformable Noise Scheduler for Diffusion ModelsAuthor 10 of 10ICML 2026
  5. ASSIST-3D: Adapted Scene Synthesis for Class-Agnostic 3D Instance SegmentationAuthor 6 of 6AAAI 2026
  6. Efficient Prediction of Large Protein Complexes via Subunit-Guided Hierarchical RefinementAuthor 4 of 6ICLR 2026
  7. Learning to See through Illumination Extremes with Event Streaming in Multimodal Large Language ModelsAuthor 9 of 10CVPR 2026
  8. QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-ResolutionAuthor 4 of 6CVPR Findings 2026
  9. Retrieval-VLA: Training-Free In-Context Adaptation for Vision-Language-Action ModelsAuthor 5 of 5CVPR Findings 2026
  10. Vision Foundation Models as Effective Visual Tokenizers for Autoregressive GenerationAuthor 8 of 11NeurIPS 2025 · 21 citations
  11. Holistic Tokenizer for Autoregressive Image GenerationAuthor 7 of 10ICCV 2025 · 11 citations
  12. NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video UnderstandingAuthor 6 of 8UIST 2025 · 6 citations
  13. Aligning Effective Tokens with Video Anomaly in Large Language ModelsAuthor 8 of 9ICCV 2025 · 2 citations
  14. A Data-Centric Revisit of Pre-Trained Vision Models for Robot LearningAuthor 5 of 5CVPR 2025
  15. Learning from Neighbors: Category Extrapolation for Long-Tail LearningAuthor 6 of 6CVPR 2025
  16. SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language ModelsAuthor 10 of 10ICML 2025
  17. RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene UnderstandingAuthor 5 of 5CVPR 2024 · 49 citations
  18. What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable InsightsAuthor 5 of 5NeurIPS 2024 · 19 citations
  19. Total-Decom: Decomposed 3D Scene Reconstruction with Minimal InteractionAuthor 5 of 5CVPR 2024 · 8 citations
  20. How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?Author 9 of 10CVPR 2024
  21. MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly DetectionAuthor 5 of 6AAAI 2023 · 221 citations
  22. Parametric Classification for Generalized Category Discovery: A Baseline StudyAuthor 3 of 3ICCV 2023 · 152 citations
  23. Texture Generation on 3D Meshes with Point-UV DiffusionAuthor 6 of 6ICCV 2023 · 78 citations
  24. IST-Net: Prior-free Category-level Pose Estimation with Implicit Space TransformationAuthor 4 of 4ICCV 2023 · 64 citations
  25. Is Synthetic Data from Generative Models Ready for Image Recognition?Author 8 of 8ICLR 2023 · 56 citations
  26. Context-Aware Transformer for 3D Point Cloud Automatic AnnotationAuthor 3 of 6AAAI 2023 · 10 citations
  27. MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point CloudsAuthor 6 of 6CVPR 2023
  28. PLA: Language-Driven Open-Vocabulary 3D Scene UnderstandingAuthor 6 of 6CVPR 2023
  29. Self-Supervised Visual Representation Learning with Semantic GroupingAuthor 5 of 5NeurIPS 2022 · 104 citations
  30. Progressive End-to-End Object Detection in Crowded ScenesAuthor 4 of 5CVPR 2022 · 82 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines