Dongxia Wang
6 papers · 2015–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(3)
🏃
Academic Marathon
(10)
🐝
Cross-Pollinator
(8)
Conferences
ACL (3)
IJCAI (2)
ICML (1)
Top co-authors
Research topics
Keywords
large language model
(2)
anomaly detection
(1)
preference alignment
(1)
safety alignment
(1)
sentence similarity
(1)
support vector machine
(1)
text embedding
(1)
recommender system
(1)
attention analysis
(1)
data distillation
(1)
tokenization robustness
(1)
text embedding model
(1)
transformer model
(1)
user simulation
(1)
sticky token detection
(1)
self-attention mechanism
(1)
vector steering
(1)
Papers
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
ACL 2026
Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
ACL 2026
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