Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
Paper β’ 2509.23371 β’ Published β’ 6 β’
1
junmingyang
jmyang
AI & ML interests
LLM Alignment, VLM
Recent Activity
updated a collection 23 days ago
Meta APO upvoted a collection 23 days ago
Meta APO updated a model 23 days ago
jmyang/MetaAPO-Qwen2.5-7BOrganizations
None yet
commented a
paper 6 months ago