Lune

Profiles2021-2026

Yibing Song

Independent Researcher

32Papers
3Last author
52Unique co-authors
0First author
0Solo

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

Recent papers32

  1. AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety BasinAuthor 9 of 10AAAI 2026 · 19 citations
  2. Advancing Textual Prompt Learning with Anchored AttributesAuthor 2 of 5ICCV 2025 · 8 citations
  3. PiCO: Peer Review in LLMs based on Consistency OptimizationAuthor 7 of 8ICLR 2025
  4. Re-Aligning Language to Visual Objects with an Agentic WorkflowAuthor 9 of 9ICLR 2025
  5. Image Inpainting via Iteratively Decoupled Probabilistic ModelingAuthor 4 of 8ICLR 2024 · 17 citations
  6. InstructDET: Diversifying Referring Object Detection with Generalized InstructionsAuthor 11 of 11ICLR 2024 · 16 citations
  7. LFME: A Simple Framework for Learning from Multiple Experts in Domain GeneralizationAuthor 3 of 6NeurIPS 2024 · 15 citations
  8. Aligning Audio-Visual Joint Representations with an Agentic WorkflowAuthor 2 of 2NeurIPS 2024 · 7 citations
  9. DiffusionDet: Diffusion Model for Object DetectionAuthor 3 of 4ICCV 2023 · 715 citations
  10. Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image SegmentationAuthor 4 of 6ICCV 2023 · 85 citations
  11. Efficient Video Action Detection with Token Dropout and Context RefinementAuthor 3 of 5ICCV 2023 · 31 citations
  12. Domain Generalization via Rationale InvarianceAuthor 3 of 5ICCV 2023 · 29 citations
  13. Soft Neighbors are Positive Supporters in Contrastive Visual Representation LearningAuthor 5 of 6ICLR 2023 · 15 citations
  14. Both Diverse and Realism Matter: Physical Attribute and Style Alignment for Rainy Image GenerationAuthor 4 of 5ICCV 2023 · 8 citations
  15. Human MotionFormer: Transferring Human Motions with Vision TransformersAuthor 9 of 11ICLR 2023 · 5 citations
  16. Advancing Visual Grounding with Scene Knowledge: Benchmark and MethodAuthor 3 of 5CVPR 2023
  17. Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space ViewpointAuthor 2 of 3CVPR 2023
  18. Improved Test-Time Adaptation for Domain GeneralizationAuthor 3 of 5CVPR 2023
  19. VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-TrainingAuthor 2 of 4NeurIPS 2022 · 2,336 citations
  20. Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake DetectionAuthor 3 of 5CVPR 2022 · 251 citations
  21. EViT: Expediting Vision Transformers via Token ReorganizationsAuthor 4 of 6ICLR 2022 · 137 citations
  22. OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time TrainingAuthor 3 of 5NeurIPS 2022 · 102 citations
  23. One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic ModulationsAuthor 3 of 8NeurIPS 2022 · 44 citations
  24. Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation LearningAuthor 3 of 6NeurIPS 2021 · 37 citations
  25. Stabilized Medical Image AttacksAuthor 3 of 5ICLR 2021 · 34 citations
  26. ArtFlow: Unbiased Image Style Transfer via Reversible Neural FlowsAuthor 3 of 6CVPR 2021
  27. DeFLOCNet: Deep Image Editing via Flexible Low-Level ControlsAuthor 4 of 8CVPR 2021
  28. Disentangled Cycle Consistency for Highly-Realistic Virtual Try-OnAuthor 2 of 6CVPR 2021
  29. IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object TrackingAuthor 2 of 4CVPR 2021
  30. Parser-Free Virtual Try-On via Distilling Appearance FlowsAuthor 2 of 7CVPR 2021

Showing the 30 most recent indexed papers.

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