Awesome AI for Science
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Wenkai Yang — most-cited papers & profile · AI for Science
← authors
·
overview
Wenkai Yang
8
papers ·
110
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
RAP: Robustness-aware Perturbations For Defending Against Backdoor Attacks On NLP Models
2021 · 58 citations
Super(ficial)-alignment: Strong Models May Deceive Weak Models In Weak-to-strong Generalization
2024 · 21 citations
Expose Backdoors On The Way: A Feature-based Efficient Defense Against Textual Backdoor Attacks
2022 · 14 citations
Distilling Rule-based Knowledge Into Large Language Models
2023 · 10 citations
LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
2025 · 7 citations
DeepCritic: Deliberate Critique with Large Language Models
2025
Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
2024
Topics
Training Techniques
Fine-Tuning
Safety & Alignment
Adversarial ML
cs.CR
Reinforcement Learning
In-Context Learning
RLHF & Alignment
Policy Gradient
Model-Based RL