PPaperPicks

Ziquan Liu

13 papers at tracked venues · 10 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Confidence Should Be Calibrated More Than One Turn Deep
  2. Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds
  3. GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models
  4. AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
  5. ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction
  6. PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
  7. Query-based Knowledge Transfer for Heterogeneous Learning Environments
  8. RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning
  9. SEBRA : Debiasing through Self-Guided Bias Ranking
  10. Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking
  11. A Secure Image Watermarking Framework with Statistical Guarantees via Adversarial Attacks on Secret Key Networks
  12. The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
    ICML 2024 · Ziquan Liu
  13. The Second Visual Object Tracking Segmentation VOTS2024 Challenge Results