PPaperPicks

Ke Yan

17 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
  2. Aigi-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models
  3. Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
  4. Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation
  5. ROD-MLLM: Towards More Reliable Object Detection in Multimodal Large Language Models
  6. SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation
    AAAI 2025 · Ke Yan
  7. ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts
  8. Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
  9. VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
  10. AlignCLIP: Align Multi Domains of Texts Input for CLIP models with Object-IoU Loss
  11. Anchor-based Robust Finetuning of Vision-Language Models
  12. Bilateral Adaptive Cross-Modal Fusion Prompt Learning for CLIP
  13. LaRE2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection
  14. MmAP: Multi-Modal Alignment Prompt for Cross-Domain Multi-Task Learning
  15. Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
  16. SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
  17. VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding