Steven Ma

mabobbi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 14 hours ago

Complex Logical Instruction Generation

Paper • 2508.09125 • Published 1 day ago • 34

commented on Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment about 1 month ago

view reply

Question: at the end of section 5.2 right above "Summary of this section", should the equation of the optimal reward function be

?
i.e I think there's an extra Z(x) in the first log term.