Lune

Profiles2022-2026

Feng Liu

The University of Melbourne

26Papers
13Last author
43Unique co-authors
0First author
0Solo

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

Recent papers26

  1. Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache OptimizationAuthor 4 of 4ACL Findings 2026 · 5 citations
  2. Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing ApproachAuthor 5 of 5ICML 2026 · 1 citation
  3. LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size AsymmetryAuthor 4 of 4ICML 2026
  4. Zero-source LLM Hallucination Detection with Human-like Criteria ProbingAuthor 4 of 6ICML 2026
  5. DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence TestingAuthor 7 of 7NeurIPS 2025 · 8 citations
  6. Generative Model Inversion Through the Lens of the Manifold HypothesisAuthor 5 of 6NeurIPS 2025 · 3 citations
  7. Anchor-based Maximum Discrepancy for Relative Similarity TestingAuthor 4 of 4NeurIPS 2025 · 2 citations
  8. Attribute-based Visual Reprogramming for Vision-Language ModelsAuthor 5 of 5ICLR 2025
  9. Deep Kernel Relative Test for Machine-generated Text DetectionAuthor 6 of 6ICLR 2025
  10. One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional DiscrepancyAuthor 4 of 4ICML 2025
  11. Sample-specific Noise Injection for Diffusion-based Adversarial PurificationAuthor 5 of 5ICML 2025
  12. Understanding Model Reprogramming for CLIP via Decoupling Visual PromptsAuthor 5 of 5ICML 2025
  13. Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?Author 4 of 8NeurIPS 2024 · 124 citations
  14. Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language ModelsAuthor 6 of 6ICML 2024 · 30 citations
  15. Bayesian-guided Label Mapping for Visual ReprogrammingAuthor 5 of 5NeurIPS 2024 · 14 citations
  16. Sample-specific Masks for Visual Reprogramming-based PromptingAuthor 5 of 5ICML 2024 · 14 citations
  17. Pseudo-Private Data Guided Model Inversion AttacksAuthor 3 of 5NeurIPS 2024 · 12 citations
  18. Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial TrainingAuthor 2 of 5ICML 2024 · 9 citations
  19. Mind the Gap Between Prototypes and Images in Cross-domain FinetuningAuthor 2 of 6NeurIPS 2024 · 4 citations
  20. Learning to Augment Distributions for Out-of-distribution DetectionAuthor 4 of 6NeurIPS 2023 · 59 citations
  21. Out-of-distribution Detection Learning with Unreliable Out-of-distribution SourcesAuthor 5 of 7NeurIPS 2023 · 53 citations
  22. Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase HypothesisAuthor 2 of 6ICCV 2023 · 19 citations
  23. Out-of-distribution Detection with Implicit Outlier TransformationAuthor 3 of 8ICLR 2023 · 10 citations
  24. Meta Discovery: Learning to Discover Novel Classes given Very Limited DataAuthor 2 of 9ICLR 2022 · 52 citations
  25. Watermarking for Out-of-distribution DetectionAuthor 2 of 7NeurIPS 2022 · 44 citations
  26. Bilateral Dependency Optimization: Defending Against Model-inversion AttacksAuthor 2 of 7KDD 2022 · 20 citations
Dusk over the sea between two cliffs drawn in fine vertical lines