wizeng23
·
AI & ML interests
None yet
Organizations
-
-
-
-
-
-
-
-
-
-
-
view article
OpenAI just dropped two massive open-weight models — *but how do we separate the reality from the hype?*
view article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment