Mitsuki Sakamoto
5 papers
· 2022–2025
· 5 conferences
· across top CS/AI conferences
Achievements
π
Interdisciplinary Bridge
π
Conference Polyglot
(5)
π
Cross-Pollinator
(9)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(14)
Conferences
AISTATS (1)
EMNLP (1)
ICLR (1)
ICML (1)
UAI (1)
Top co-authors
Keywords
nash equilibrium
(2)
zero-sum game
(2)
language model alignment
(1)
reinforcement learning from human feedback
(1)
model alignment
(1)
convergence guarantee
(1)
language model
(1)
last-iterate convergence
(1)
reward model
(1)
multiplicative weights update
(1)
noisy gradient
(1)
preference dataset
(1)
text quality
(1)
game theory
(1)
noisy feedback
(1)
direct preference optimization
(1)
Papers
Filtered Direct Preference Optimization
EMNLP 2024