Lune

Profiles2022-2026ORCID 0000-0002-8276-2679

Xu Yang

Ministry of Education

22Papers
5Last author
33Unique co-authors
2First author
0Solo

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

Recent papers22

  1. Adaptive-Learngene: Continual Expansion and Task-Aware Selection of Learngenes for Dynamic EnvironmentsAuthor 4 of 5AAAI 2026
  2. Breaking Semantic Boundaries: Distribution-Guided Semantic Exploration for Creative GenerationAuthor 4 of 6CVPR 2026
  3. Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable KnowledgeAuthor 4 of 5AAAI 2026
  4. Inheriting Generalizable Knowledge from LLMs to Diverse Vertical TasksAuthor 3 of 5ICLR 2026
  5. UNITE: Universal kNowledge Integration from Task-specific ExpertsAuthor 3 of 4ICLR 2026
  6. Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial ImputationAuthor 3 of 4NeurIPS 2025 · 6 citations
  7. FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow NetworkAuthor 5 of 5NeurIPS 2025 · 1 citation
  8. Enhancing Multimodal In-Context Learning for Image Classification through Coreset OptimizationAuthor 5 of 5ACM MM 2025
  9. Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple TasksAuthor 3 of 6AAAI 2025
  10. Mimic In-Context Learning for Multimodal TasksAuthor 7 of 7CVPR 2025
  11. Redefining in Dictionary: Towards an Enhanced Semantic Understanding of Creative GenerationAuthor 3 of 5CVPR 2025
  12. Transformer as Linear Expansion of LearngeneAuthor 3 of 6AAAI 2024 · 14 citations
  13. Lever LM: Configuring In-Context Sequence to Lever Large Vision Language ModelsAuthor 1 of 7NeurIPS 2024 · 13 citations
  14. Cluster-Learngene: Inheriting Adaptive Clusters for Vision TransformersAuthor 2 of 5NeurIPS 2024 · 10 citations
  15. Initializing Variable-sized Vision Transformers from Learngene with Learnable TransformationAuthor 3 of 4NeurIPS 2024 · 9 citations
  16. Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale ModelsAuthor 5 of 6NeurIPS 2024 · 7 citations
  17. Vision Transformers as Probabilistic Expansion from LearngeneAuthor 3 of 6ICML 2024 · 6 citations
  18. Building Variable-Sized Models via Learngene PoolAuthor 3 of 6AAAI 2024 · 5 citations
  19. How to Configure Good In-Context Sequence for Visual Question AnsweringAuthor 5 of 5CVPR 2024
  20. LIVE: Learnable In-Context Vector for Visual Question AnsweringAuthor 6 of 6NeurIPS 2024
  21. Exploring Diverse In-Context Configurations for Image CaptioningAuthor 1 of 5NeurIPS 2023 · 104 citations
  22. Towards Unbiased Visual Emotion Recognition via Causal InterventionAuthor 2 of 3ACM MM 2022 · 27 citations
Dusk over the sea between two cliffs drawn in fine vertical lines