Lune

Profiles2021-2026

Lingjuan Lyu

Sony AI

50Papers
11Last author
90Unique co-authors
0First author
0Solo

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

Recent papers50

  1. Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation ModelsAuthor 3 of 7AAAI 2026 · 1 citation
  2. UniCompress: Token Compression for Unified Vision-Language Understanding and GenerationAuthor 7 of 7CVPR 2026 · 1 citation
  3. UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained ModelsAuthor 6 of 7CVPR Findings 2026
  4. StelLA: Subspace Learning in Low-rank Adaptation using Stiefel ManifoldAuthor 4 of 4NeurIPS 2025 · 16 citations
  5. Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation PerspectiveAuthor 4 of 7AAAI 2025 · 5 citations
  6. Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated LearningAuthor 3 of 5AAAI 2025 · 3 citations
  7. Asymmetrical Reciprocity-based Federated Learning for Resolving Disparities in Medical DiagnosisAuthor 3 of 4KDD 2025 · 2 citations
  8. MixA: A Mixed Attention Approach with Stable Lightweight Linear Attention to Enhance Efficiency of Vision Transformers at the EdgeAuthor 5 of 5ICCV 2025 · 2 citations
  9. CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion ModelsAuthor 3 of 4ACM MM 2025 · 1 citation
  10. CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIAuthor 2 of 6CVPR 2025
  11. Enhancing Foundation Models with Federated Domain Knowledge InfusionAuthor 5 of 6ICML 2025
  12. How to Evaluate and Mitigate IP Infringement in Visual Generative AI?Author 5 of 5ICML 2025
  13. Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and VarietyAuthor 4 of 6CVPR 2025
  14. Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion ModelsAuthor 8 of 8CVPR 2025
  15. Stretching Each Dollar: Diffusion Training from Scratch on a Micro-BudgetAuthor 5 of 6CVPR 2025
  16. Detecting, Explaining, and Mitigating Memorization in Diffusion ModelsAuthor 4 of 4ICLR 2024 · 103 citations
  17. How to Trace Latent Generative Model Generated Images without Artificial Watermark?Author 4 of 8ICML 2024 · 24 citations
  18. FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model HeterogeneityAuthor 4 of 5ICLR 2024 · 18 citations
  19. FedWon: Triumphing Multi-domain Federated Learning Without NormalizationAuthor 2 of 2ICLR 2024 · 13 citations
  20. DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion ModelsAuthor 3 of 5ICLR 2024 · 12 citations
  21. COALA: A Practical and Vision-Centric Federated Learning PlatformAuthor 5 of 5ICML 2024 · 10 citations
  22. pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated LearningAuthor 3 of 4NeurIPS 2024 · 5 citations
  23. FedMef: Towards Memory-Efficient Federated Dynamic PruningAuthor 4 of 4CVPR 2024
  24. TARGET: Federated Class-Continual Learning via Exemplar-Free DistillationAuthor 4 of 5ICCV 2023 · 109 citations
  25. Towards Personalized Federated Learning via Heterogeneous Model ReassemblyAuthor 5 of 7NeurIPS 2023 · 102 citations
  26. UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error DecompositionAuthor 5 of 8NeurIPS 2023 · 90 citations
  27. Delving into the Adversarial Robustness of Federated LearningAuthor 4 of 7AAAI 2023 · 62 citations
  28. Where Did I Come From? Origin Attribution of AI-Generated ImagesAuthor 4 of 6NeurIPS 2023 · 44 citations
  29. Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor WatermarkAuthor 6 of 10ACL 2023 · 39 citations
  30. Byzantine-Robust Learning on Heterogeneous Data via Gradient SplittingAuthor 3 of 6ICML 2023 · 27 citations

Showing the 30 most recent indexed papers.

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