PPaperPicks

Xu Yang

Southeast University, Nanjing, China

24 papers at tracked venues · 22 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Adaptive-Learngene: Continual Expansion and Task-Aware Selection of Learngenes for Dynamic Environments
  2. Efficient and Effective In-context Demonstration Selection with Coreset
  3. Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge
  4. GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning
  5. Learngene: Inheritable 'Genes' in Intelligent Agents (Abstract Reprint)
  6. Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization
  7. Fast Large Language Model Collaborative Decoding via Speculation
  8. FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow Network
  9. Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple Tasks
  10. Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales
  11. Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks
  12. Redefining in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation
  13. Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
  14. Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark
  15. Building Variable-Sized Models via Learngene Pool
  16. Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
  17. Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models
  18. How to Configure Good In-Context Sequence for Visual Question Answering
  19. Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
  20. LIVE: Learnable In-Context Vector for Visual Question Answering
  21. Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
    NeurIPS 2024 · Xu Yang
  22. Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
  23. Transformer as Linear Expansion of Learngene
  24. Vision Transformers as Probabilistic Expansion from Learngene