Lune

Profiles2021-2026

Yujun Shen

Ant Group

21Papers
1Last author
58Unique co-authors
0First author
0Solo

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

Recent papers21

  1. PlanGS: Active 3D Gaussian Reconstruction with Real-Time PlanningAuthor 4 of 5CVPR Findings 2026
  2. Lipschitz Singularities in Diffusion ModelsAuthor 4 of 11ICLR 2024 · 27 citations
  3. A Recipe for Scaling up Text-to-Video Generation with Text-free VideosAuthor 7 of 9CVPR 2024 · 19 citations
  4. GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View SynthesisAuthor 4 of 9SIGGRAPH 2024 · 17 citations
  5. Ranni: Taming Text-to-Image Diffusion for Accurate Instruction FollowingAuthor 4 of 6CVPR 2024
  6. VideoComposer: Compositional Video Synthesis with Motion ControllabilityAuthor 7 of 9NeurIPS 2023 · 579 citations
  7. Composer: Creative and Controllable Image Synthesis with Composable ConditionsAuthor 4 of 6ICML 2023 · 371 citations
  8. Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from BackboneAuthor 6 of 8NeurIPS 2023 · 31 citations
  9. Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long VideosAuthor 5 of 7ICCV 2023 · 29 citations
  10. FaceComposer: A Unified Model for Versatile Facial Content CreationAuthor 6 of 8NeurIPS 2023 · 14 citations
  11. ViM: Vision Middleware for Unified Downstream TransferringAuthor 5 of 7ICCV 2023 · 2 citations
  12. Balancing Logit Variation for Long-Tailed Semantic SegmentationAuthor 8 of 8CVPR 2023
  13. Dimensionality-Varying Diffusion ProcessAuthor 7 of 10CVPR 2023
  14. LipFormer: High-fidelity and Generalizable Talking Face Generation with A Pre-learned Facial CodebookAuthor 5 of 7CVPR 2023
  15. Neural Dependencies Emerging from Learning Massive CategoriesAuthor 4 of 10CVPR 2023
  16. VideoFusion: Decomposed Diffusion Models for High-Quality Video GenerationAuthor 6 of 9CVPR 2023
  17. A Unified Model for Multi-class Anomaly DetectionAuthor 3 of 7NeurIPS 2022 · 585 citations
  18. Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-LabelsAuthor 3 of 9CVPR 2022 · 448 citations
  19. 3D-aware Image Synthesis via Learning Structural and Textural RepresentationsAuthor 4 of 5CVPR 2022 · 88 citations
  20. Learning from Future: A Novel Self-Training Framework for Semantic SegmentationAuthor 2 of 9NeurIPS 2022 · 40 citations
  21. Low-Rank Subspaces in GANsAuthor 3 of 7NeurIPS 2021 · 80 citations
Dusk over the sea between two cliffs drawn in fine vertical lines