Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
Paper
•
2509.23371
•
Published
•
6
•
1
junmingyang
jmyang
AI & ML interests
LLM Alignment, VLM
Recent Activity
upvoted
a
paper
about 2 months ago
DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
authored
a paper
4 months ago
VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality
Models
authored
a paper
4 months ago
Alignment through Meta-Weighted Online Sampling: Bridging the Gap
between Data Generation and Preference Optimization
Organizations
None yet
commented
a
paper
4 months ago