Luyao Niu
12 papers · 2023–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (5) π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (20)
π
Conference Polyglot
(7)
π€
Dynamic Duo
(10)
π
Century Club
(10)
β‘
Prolific Year
(5)
Conferences
ACL (6)
AAAI (1)
EMNLP (1)
ICLR (1)
IJCAI (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
large language model
(8)
safety alignment
(3)
adversarial learning
(3)
jailbreak attack
(3)
knowledge distillation
(2)
chain-of-thought reasoning
(2)
decoding strategy
(2)
adversarial attack
(2)
llm safety
(2)
instruction tuning
(2)
backdoor attack
(2)
gaussian process
(1)
harmful content
(1)
model safety
(1)
model robustness
(1)
safety evaluation
(1)
adversarial training
(1)
social network
(1)
adversarial prompt
(1)
text generation
(1)
Papers
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
ACL 2026
Temporal Sampling for Forgotten Reasoning in LLMs
ACL 2026
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
ICLR 2025
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
ACL 2025
Small Models Struggle to Learn from Strong Reasoners
ACL 2025
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
AAAI 2025
Stronger Models are Not Always Stronger Teachers for Instruction Tuning
NAACL 2025
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
EMNLP 2024
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
ACL 2024
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
ACL 2024
Learning Dissemination Strategies for External Sources in Opinion Dynamic Models with Cognitive Biases
IJCAI 2023
FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning
NIPS 2023