Lune

Profiles2020-2026ORCID 0000-0001-7673-8325

Ying Shan

ARC Lab

46Papers
10Last author
91Unique co-authors
1First author
0Solo

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

Recent papers46

  1. Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language ModelsAuthor 6 of 7CVPR 2026 · 10 citations
  2. Pixal3D: Pixel-Aligned 3D Generation from ImagesAuthor 2 of 10SIGGRAPH 2026 · 1 citation
  3. MMhops-R1: Multimodal Multi-hop ReasoningAuthor 9 of 10AAAI 2026
  4. CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition AbilitiesAuthor 7 of 8AAAI 2025 · 62 citations
  5. Cobra: Efficient Line Art COlorization with BRoAder ReferencesAuthor 1 of 3SIGGRAPH 2025 · 2 citations
  6. VisionMath: Vision-Form Mathematical Problem-SolvingAuthor 11 of 12ICCV 2025 · 2 citations
  7. MotionCtrl: A Unified and Flexible Motion Controller for Video GenerationAuthor 5 of 8SIGGRAPH 2024 · 123 citations
  8. RecDCL: Dual Contrastive Learning for RecommendationAuthor 6 of 8WWW 2024 · 63 citations
  9. DiffEditor: Boosting Accuracy and Flexibility on Diffusion-Based Image EditingAuthor 4 of 5CVPR 2024 · 36 citations
  10. SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion ModelAuthor 6 of 7AAAI 2024 · 24 citations
  11. HumanRef: Single Image to 3D Human Generation via Reference-Guided DiffusionAuthor 5 of 6CVPR 2024 · 15 citations
  12. A Pre-convolved Representation for Plug-and-Play Neural Illumination FieldsAuthor 7 of 8AAAI 2024 · 3 citations
  13. SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D ImagesAuthor 3 of 3AAAI 2024 · 2 citations
  14. SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and SynopsesAuthor 8 of 10ACM MM 2024 · 2 citations
  15. BT-Adapter: Video Conversation is Feasible Without Video Instruction TuningAuthor 5 of 6CVPR 2024
  16. GS-IR: 3D Gaussian Splatting for Inverse RenderingAuthor 4 of 5CVPR 2024
  17. How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?Author 8 of 10CVPR 2024
  18. Mitigating Artifacts in Real-World Video Super-resolution ModelsAuthor 6 of 6AAAI 2023 · 42 citations
  19. Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text RetrievalAuthor 6 of 6AAAI 2023 · 39 citations
  20. PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline PanoramasAuthor 5 of 6NeurIPS 2023 · 28 citations
  21. Exploring Model Transferability through the Lens of Potential EnergyAuthor 4 of 5ICCV 2023 · 15 citations
  22. OmniZoomer: Learning to Move and Zoom in on Sphere at High-ResolutionAuthor 4 of 6ICCV 2023 · 8 citations
  23. Accelerating the Training of Video Super-resolution ModelsAuthor 4 of 4AAAI 2023 · 4 citations
  24. Order-Prompted Tag Sequence Generation for Video TaggingAuthor 10 of 11ICCV 2023 · 3 citations
  25. Accelerating Vision-Language Pretraining with Free Language ModelingAuthor 5 of 9CVPR 2023
  26. DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking TasksAuthor 5 of 6CVPR 2023
  27. HRDFuse: Monocular 360° Depth Estimation by Collaboratively Learning Holistic-with-Regional Depth DistributionsAuthor 4 of 5CVPR 2023
  28. Improved Test-Time Adaptation for Domain GeneralizationAuthor 4 of 5CVPR 2023
  29. LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image GenerationAuthor 5 of 6CVPR 2023
  30. OSRT: Omnidirectional Image Super-Resolution with Distortion-aware TransformerAuthor 5 of 6CVPR 2023

Showing the 30 most recent indexed papers.

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