Portrait of Sheng Zhang

Sheng Zhang

Principal Researcher

Connect on LinkedIn

About

I am a Principal Research Lead at Microsoft Research, where I build foundation models and frontier AI systems for multimodal reasoning and real-world applications.

My work includes foundation models used by millions of people (BiomedCLIP (opens in new tab), Curiosity (opens in new tab), GigaPath (opens in new tab)); test-time scaling methods for OpenAI frontier models (MedPrompt (opens in new tab)); and agent harnesses that extend LLMs to new modalities (Be My Eyes (opens in new tab)).

I also develop new post-training paradigms and data recipes (LLaVA-Med (opens in new tab), OctoMed (opens in new tab)), and post-train models that address real-world problems frontier LLMs cannot yet solve (UniRG (opens in new tab)). I am fortunate to work with talented students and collaborators on a range of exciting research directions.

Selected Publications

External: Google Scholar (opens in new tab)

Click for full publications

Tutorials

Service

  • Area Chair: NeurIPS 2023; ARR; ACL 2024; NAACL 2021, 2024; EMNLP 2022; IJCNLP-AACL 2023
  • Tutorial: KDD 2023
  • Organizer: Workshop on COmmonsense INference in NLP (opens in new tab) (COIN) at EMNLP 2019
  • (S)PC Member/Reviewer: ACL 2017–2023; EMNLP 2018–2021; AAAI 2020–2024; CVPR 2025; ICCV 2023–2025; NAACL 2018–2021; EACL 2017, 2021; AACL-IJCNLP 2020; COLM 2024; COLING 2020; CoNLL 2019; IJCNLP 2017; IWCS 2017; TACL; Computational Linguistics; ARR; BMC Bioinformatics; NLE

Personal webpage: https://sheng-z.github.io/ (opens in new tab)