Josef Dai
8 papers
· 2023–2025
· 4 conferences
· across top CS/AI conferences
Achievements
π£
Hot Topic Early Bird
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(4)
π
Cross-Pollinator
(7)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(20)
β‘
Prolific Year
(5)
Conferences
ACL (4)
NIPS (2)
AAAI (1)
ICLR (1)
Top co-authors
Keywords
reinforcement learning from human feedback
(4)
large language model
(3)
reward modeling
(2)
safety alignment
(2)
human preference
(2)
language model alignment
(2)
responsible ai
(1)
model alignment
(1)
data compression
(1)
safe reinforcement learning
(1)
bayesian network
(1)
sequence-to-sequence learning
(1)
safety evaluation
(1)
safety benchmark
(1)
preference datum
(1)
alignment fine-tuning
(1)
model elasticity
(1)
pre-training distribution
(1)
harmful output mitigation
(1)
safe policy optimization
(1)