Dongxia Wang

4 papers · 2015–2025 · 3 conferences · across top CS/AI conferences

Achievements

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🏃 Academic Marathon (10) 🐝 Cross-Pollinator (8)

Conferences

IJCAI (2) ACL (1) ICML (1)

Top co-authors

Yang Liu (2) Kexin Chen (1) Qing Guo (1) Tim Muller (1) Yi Liu (1) Jie Zhang (1) Wenhai Wang (1) Haonan Zhang (1) Qi Zhou (1) Yun Lin (1)

Research topics

Optimization & Theory (1)

Keywords

self-attention mechanism (1) anomaly detection (1) sentence similarity (1) text embedding (1) attention analysis (1) tokenization robustness (1) text embedding model (1) transformer model (1) sticky token detection (1)

Papers

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models ACL 2025

Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision ICML 2025

Quantifying Robustness of Trust Systems against Collusive Unfair Rating Attacks Using Information Theory IJCAI 2015

Quantifying and Improving the Robustness of Trust Systems IJCAI 2015