Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 132
Jiangyong Huang
huangjy-pku
AI & ML interests
General-purpose Vision, Multi-modal Learning, Scene Understanding, Embodied Agent
Recent Activity
updated a dataset about 2 months ago
huangjy-pku/3D-RFT-Reasoning published a dataset about 2 months ago
huangjy-pku/3D-RFT-Reasoning updated a dataset 5 months ago
huangjy-pku/LEO-VLOrganizations
