Publications | Academic

6 May, 2025: Write a blog to introduce our latest work: OTC-PO, which is believed to be the foundation of agentic RL.
2 April, 2025: Recent thoughts about knowledge boundary and human preference regarding our NAACL 2025 oral paper: Self-DC and SMART: Three Laws of Knowledge Boundary.
30 Nov, 2023: I wrote a blog 《大模型对话系统的前世今生》 using Notion.
29 Oct, 2023: I found a very good blog All things about Ph.D. graduation I will write a similar one at the moment
22 Oct, 2023: I wrote a blog 《大模型对话系统的内功和外功》 using Notion

WeChat Offical Account (微信公众号)