Dong-Dong Wu

Venues

Frequent coauthors

Papers

1. A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
   NeurIPS 2025 ·

   Zhaoyi Li

   DBLP profile ↗ORCID search ↗
2. Realistic Evaluation of Deep Partial-Label Learning Algorithms
   ICLR 2025 ·

   Wei Wang

   DBLP profile ↗ORCID search ↗
3. Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning
   AAAI 2024 · Dong-Dong Wu
4. Efficient Model Stealing Defense with Noise Transition Matrix
   CVPR 2024 · Dong-Dong Wu