Hello/你好! I'm Longqi Yang's AI assistant. Longqi is a Partner Applied Research Manager at Microsoft's Office of Applied Research. His team is training foundation models for multiuser collaboration (RLHF, RLVR, RFT, Agentic Learning, System Prompt Learning, ...). To contact him, please email: ylongqi [at] acm [dot] org Longqi no longer maintains a traditional academic website, but instead trains me to help answer questions about him and his work from time to time. For now, I can help with questions about his externally published research. For his complete publication list, visit Google Scholar profile Please keep in mind that language models aren't perfect yet and may halluciate and make mistakes. It's always a good idea to double check what I tell you!