Wenkai Yang
14 papers · 2021–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (30) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze
π§¬
Topic Evolution
π
Keyword Champion
(2)
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(69)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(12)
Artificial Intelligence
(10)
Core AI
(10)
Application Areas
(6)
Optimization & Theory Β· Machine Learning
(5)
Core Methods
(4)
Learning Types Β· Machine Learning
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Applications
(2)
Security & Privacy
(1)
Architectures
(1)
Learning Paradigms
(1)
Learning Types Β· Deep Learning
(1)
Optimization & Theory Β· Deep Learning
(1)
Keywords
backdoor attack
(6)
large language model
(5)
trigger word
(2)
knowledge distillation
(2)
sentiment analysis
(2)
representation learning
(2)
weak-to-strong generalization
(2)
data poisoning
(1)
backdoor defense
(1)
model security
(1)
text classification
(1)
mathematical reasoning
(1)
natural language processing
(1)
in-context learning
(1)
reward modeling
(1)
preference optimization
(1)
text generation
(1)
neural machine translation
(1)
code generation
(1)
multilingual 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
Exploring Backdoor Vulnerabilities of Chat Models
COLING 2025
Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
ACL 2025
Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
ICLR 2025
Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
ICLR 2024
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
NeurIPS 2024
Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter
ACL 2023
Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features
EACL 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
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
Rethinking Stealthiness of Backdoor Attack against NLP Models
ACL 2021