OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
Paper • 2603.28858 • Published • 6
Haiyue Song
shyyhs
AI & ML interests
machine translation, subword
Recent Activity
submitted a paper 3 days ago
OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training upvoted a paper 4 months ago
Structured Document Translation via Format Reinforcement LearningOrganizations
None yet
submitted a
paper to Daily Papers 3 days ago
submitted a
paper to Daily Papers 4 months ago
authored a
paper 4 months ago