Wenlong Wang

Wenlong Wang is a Research Scientist at Meta, specializing in multi-modal and media inference since October 2025. In addition to this role, Wenlong contributes to the vLLM project as an open source contributor, focusing on multi-modal support and speculative decoding. Previous experience includes a brief internship at Google, where work involved the core development of the JAX backend for vLLM using TPU, and research as a Graduate Research Assistant at the University of Minnesota under Prof. David Du, with a focus on intelligent storage from 2019 to 2025. Wenlong has also interned at Futurewei Technologies, researching updatable Learned Indexes and improving system efficiency, and at Alibaba Group, optimizing Flash Translation Layer mapping in SSDs. Early experience includes a software engineering internship at Hututa Technologies Limited, where database storage structures were analyzed and improved. Wenlong holds a PhD in Computer Science and Engineering from the University of Minnesota and a Bachelor's degree from The Hong Kong University of Science and Technology.