
Qwen3-14B DEX experiments compare GRPO, DAPO, GDPO, CISPO, ADAPO and REPO-R with and without thinking: full holdout results, reward curves, time and memory.
Ex-Apple GenAI engineer, building an LLM post-training platform at g factor technologies
Ex-Apple GenAI engineer, building an LLM post-training platform at g factor technologies
Markdown supported · ⌘↵ to post
No responses yet.