PPaperPicks

Yuhua Li

Huazhong University of Science and Technology, School of Computer Science, and Technology, Wuhan, China

30 papers at tracked venues · 28 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning
  2. EchoMLLM: Incentivizing Echocardiographic Video Understanding with Keyframe Grounding and Report Generation
  3. Language-Guided Game-Theoretic Fairness in Web-Enabled Energy Networks
  4. UMPIRE: Unveiling LLM-generated Posts via Redundant Expressions
  5. Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
  6. Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
  7. Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
  8. ChatbotID: Identifying Chatbots with Granger Causality Test
  9. FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
  10. Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
  11. Random Registers for Cross-Domain Few-Shot Learning
  12. Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning
  13. Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
  14. Revisiting Pool-Based Prompt Learning for Few-Shot Class-Incremental Learning
  15. Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
  16. The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
  17. The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
  18. A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning
  19. Adversarial Attack for Explanation Robustness of Rationalization Models
  20. Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning
  21. Compositional Few-Shot Class-Incremental Learning
  22. Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning
  23. FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
  24. Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
  25. Generate Universal Adversarial Perturbations for Few-Shot Learning
  26. Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-shot Open-Set Recognition
  27. Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
  28. MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
  29. Masked Graph Autoencoder with Non-discrete Bandwidths
  30. Masked Random Noise for Communication-Efficient Federated Learning