PPaperPicks

Sanghyuk Chun

12 papers at tracked venues · 7 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. An Efficient Post-Hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
  2. Probabilistic Language-Image Pre-Training
    ICLR 2025 · Sanghyuk Chun
  3. Read, Watch and Scream! Sound Generation from Text and Video
  4. Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? - A Theoretical and Empirical Study
  5. HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
  6. Improved Probabilistic Image-Text Representations
    ICLR 2024 · Sanghyuk Chun
  7. Language-only Efficient Training of Zero-shot Composed Image Retrieval
  8. Learning with Unmasked Tokens Drives Stronger Vision Learners
  9. RoCOCO: Robustness Benchmark of MS-COCO to Stress-Test Image-Text Matching Models
  10. Similarity of Neural Architectures Using Adversarial Attack Transferability
  11. Toward Interactive Regional Understanding in Vision-Large Language Models
  12. What does automatic differentiation compute for neural networks?