Lune

Profiles2021-2026

Yao Zhu

Zhejiang University

16Papers
7Last author
29Unique co-authors
1First author
0Solo

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

Recent papers16

  1. Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language ModelsAuthor 6 of 6ICLR 2026 · 4 citations
  2. Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMsAuthor 10 of 10AAAI 2026 · 4 citations
  3. Transferable and Stealthy Adversarial Attacks on Large Vision-Language ModelsAuthor 2 of 3ICLR 2026 · 2 citations
  4. Adaptive Nonlinear Compression for Large Foundation ModelsAuthor 4 of 6ICLR 2026
  5. Dual-Seed Evolutionary Algorithm for Noise Optimization in Diffusion ModelsAuthor 3 of 8AAAI 2026
  6. FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-Calibration for Cattle Mounting Pose EstimationAuthor 7 of 9CVPR Findings 2026
  7. Phantom: Physical Object Interactions as Dynamic Triggers for NMS-Exploited BackdoorsAuthor 4 of 14CVPR 2026
  8. Prompt-driven Small Object Instance Segmentation in Earth ObservationAuthor 5 of 5CVPR Findings 2026
  9. SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language ModelsAuthor 3 of 7ICCV 2025 · 4 citations
  10. An Efficient Framework for Enhancing Discriminative Models via Diffusion TechniquesAuthor 6 of 6AAAI 2025 · 2 citations
  11. Bridging the Gap Between Ideal and Real-World Evaluation: Benchmarking AI-Generated Image Detection in Challenging ScenariosAuthor 8 of 8ICCV 2025 · 2 citations
  12. Towards Annotation-Free Evaluation: KPAScore for Human Keypoint DetectionAuthor 6 of 6ICCV 2025 · 2 citations
  13. Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image SynthesisAuthor 7 of 7CVPR 2025
  14. Towards Understanding How Knowledge Evolves in Large Vision-Language ModelsAuthor 3 of 7CVPR 2025
  15. ImageNet-E: Benchmarking Neural Network Robustness via Attribute EditingAuthor 3 of 6CVPR 2023
  16. Towards Understanding the Generative Capability of Adversarially Robust ClassifiersAuthor 1 of 6ICCV 2021 · 30 citations
Dusk over the sea between two cliffs drawn in fine vertical lines