Zixuan Ke is a research scientist based in the San Francisco Bay Area with a decade of experience advancing autonomous, agentic systems through deep work in reasoning, LLM post-training, continual learning, and NLP. Now at Salesforce Research after a PhD at University of Illinois Chicago, Zixuan has a strong publication record across top venues (ICLR, NeurIPS, ICML, ACL, EMNLP) and internships at DeepMind, Meta, and Amazon that bridged academic rigor with applied system-building. His recent work focuses on aligning retrieval and LLM behavior and enabling agents to adapt in changing domains, reflecting a practical bent toward robust, deployable models. Notably, he blends classical argument-mining roots with cutting-edge agent and continual-learning methods, showing both breadth and a sustained record of evolving research themes.
10 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Illinois Chicago
Code for NeurIPS 2020 Paper --- Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
Contributions:2 commits, 10 pushes, 1 branch in 1 year 1 month
pytorchsequenceneurips-2020similardeep-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.