Wenkai Yang
15 papers · 2021–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Cross-Pollinator (13) π Renaissance Researcher (5) π Conference Polyglot (9) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (29)
πΊοΈ
Taxonomy Completionist
(29)
π§
Keyword Pioneer
π
Keyword Champion
(3)
π€
Dynamic Duo
(10)
π
Century Club
(14)
ποΈ
Keyword Collector
(56)
π₯
Unstoppable
(5)
Conferences
ACL (4)
COLING (2)
EMNLP (2)
ICLR (2)
AAAI (1)
EACL (1)
IJCNLP (1)
NAACL (1)
NIPS (1)
Top co-authors
Research topics
Keywords
backdoor attack
(7)
large language model
(4)
trigger word
(3)
sentiment analysis
(3)
representation learning
(2)
negative data augmentation
(2)
knowledge distillation
(2)
stealthiness evaluation
(2)
data poisoning
(1)
backdoor defense
(1)
model security
(1)
mathematical reasoning
(1)
text classification
(1)
in-context learning
(1)
natural language processing
(1)
adversarial robustness
(1)
weak supervision
(1)
code generation
(1)
neural network optimization
(1)
neural machine translation
(1)
Papers
CURE: Critique-Driven Unified Reinforcement Learning for Test-Time Self-Improvement
ACL 2026
Distilling Rule-based Knowledge into Large Language Models
COLING 2025
Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
ICLR 2025
Exploring Backdoor Vulnerabilities of Chat Models
COLING 2025
Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
ACL 2025
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
NIPS 2024
Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
ICLR 2024
Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features
EACL 2023
Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter
ACL 2023
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
EMNLP 2022
Well-Classified Examples Are Underestimated in Classification with Deep Neural Networks
AAAI 2022
Rethinking Stealthiness of Backdoor Attack against NLP Models
ACL 2021
Rethinking Stealthiness of Backdoor Attack against NLP Models
IJCNLP 2021
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
NAACL 2021
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
EMNLP 2021