MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Paper
•
2507.21183
•
Published
•
14
Eric Lan
Eric-Lan
·
AI & ML interests
Reinforcement Fine-Tuning, Reinforcement Learning, RLHF/VR, LLM Alignment, Reasoning, Diffusion Model, Speculative Decoding, Federated Learning
Recent Activity
liked
a model
15 days ago
huseyinatahaninan/Qwen2.5-7B-Instruct-CI
liked
a dataset
about 1 month ago
Eric-Lan/healthbench_axe
updated
a dataset
about 1 month ago
Eric-Lan/healthbench_axe
Organizations
authored
a
paper
5 months ago
authored
a
paper
about 1 year ago