Guanlin Liu
4 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (3) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
NIPS (2)
ICML (1)
NAACL (1)
Top co-authors
Keywords
action poisoning
(2)
adversarial attack
(2)
text generation
(1)
black-box attack
(1)
regret bound
(1)
sublinear regret
(1)
inference optimization
(1)
sampling method
(1)
response diversity
(1)
alignment training
(1)
reward poisoning
(1)
large language model
(1)
inference sampling
(1)
execution sampling
(1)
multi-agent reinforcement learning
(1)
mixed attack strategy
(1)
reinforcement learning
(1)
Papers
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
NAACL 2025
Risk-Sensitive Reward-Free Reinforcement Learning with CVaR
ICML 2024
Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning
NIPS 2023
Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning
NIPS 2021