Developed models including Skywork-Reward (indirectly Skywork-Critic), Skywork-o1/PRM, Skywork-OR1, Skywork-Reward-V2, Skywork-DeepResearch, and their previous flagship model and the current agent system.
Research Experience
During his PhD, he spent time at 2050 Research, Skywork AI, focusing exclusively on delivering effective data pipelines. This led to several open model series.
Education
Ph.D. student in Computer Science and Engineering at the University of California, Santa Cruz, advised by Yang Liu and Jeffrey Flanigan.
Background
Research interests: large language model post-training, alignment, and agents. Also works on LLM unlearning.