PPaperPicks

Nojun Kwak

25 papers at tracked venues · 18 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings
  2. Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
  3. PedaCo-Gen: Scaffolding Pedagogical Agency in Human-AI Collaborative Video Authoring
  4. Targeted Data Protection for Diffusion Model by Matching Training Trajectory
  5. Unlocking the Potential of Diffusion Language Models through Template Infilling
  6. ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-shot Object Rendering
  7. Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
  8. Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization
  9. ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
  10. Style Composition Within Distinct LoRA Modules for Traditional Art
  11. TPD-STR: Text Polygon Detection with Split Transformers
  12. Understanding Differential Transformer Unchains Pretrained Self-Attentions
  13. Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization
  14. What's Making That Sound Right Now? Video-Centric Audio-Visual Localization
  15. A Revisit to the Decoder for Camouflaged Object Detection
  16. Advancing Beyond Identification: Multi-bit Watermark for Large Language Models
  17. Any-Way Meta Learning
  18. Coreset Selection for Object Detection
  19. Deep Support Vectors
  20. MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline
  21. NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
  22. Practical Dataset Distillation Based on Deep Support Vectors
  23. Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
  24. SAVE: Protagonist Diversification with Structure Agnostic Video Editing
  25. What, How, and When Should Object Detectors Update in Continually Changing Test Domains?