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)
- BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs (opens in new tab) NEJM AI
Sheng Zhang*, Yanbo Xu (opens in new tab)*, Naoto Usuyama (opens in new tab), Hanwen Xu (opens in new tab), Jaspreet Bagga (opens in new tab), Robert Tinn (opens in new tab), Sam Preston, Rajesh Rao, Mu Wei (opens in new tab), Naveen Valluri (opens in new tab), Cliff Wong, Andrea Tupini, Yu Wang, Matt Mazzola, Swadheen Shukla, Lars Liden, Jianfeng Gao, Angela Crabtree, Brian Piening, Carlo Bifulco, Matthew P. Lungren (opens in new tab), Tristan Naumann, Sheng Wang (opens in new tab), Hoifung Poon (*equal contribution)
[ Model (opens in new tab) | Data (opens in new tab) ] - LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day (opens in new tab) NeurIPS 2023 (Spotlight)
Chunyuan Li (opens in new tab)*, Cliff Wong*, Sheng Zhang*, Naoto Usuyama (opens in new tab), Haotian Liu (opens in new tab), Jianwei Yang (opens in new tab), Tristan Naumann, Hoifung Poon, Jianfeng Gao (*equal contribution)
[ Project page (opens in new tab) ] - OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning (opens in new tab) CVPR 2026
Timothy Ossowski (opens in new tab)*, Sheng Zhang*, Qianchu Liu, Guanghui Qin (opens in new tab), Reuben Tan (opens in new tab), Tristan Naumann, Junjie Hu (opens in new tab), Hoifung Poon (*equal contribution)
[ Model (opens in new tab) | Blog (opens in new tab) | Data (opens in new tab) ] - Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration (opens in new tab)
James Y. Huang (opens in new tab)*, Sheng Zhang*, Qianchu Liu, Guanghui Qin (opens in new tab), Tinghui Zhu (opens in new tab), Tristan Naumann, Muhao Chen (opens in new tab), Hoifung Poon (*equal contribution)
[ Blog (opens in new tab) ] - Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine (opens in new tab)
Harsha Nori*, Yin Tat Lee*, Sheng Zhang*, Dean Carignan, Richard Edgar, Nicolo Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama (opens in new tab), Chris White, Eric Horvitz (opens in new tab) (*equal contribution)
[ Blog | Code (opens in new tab) ] - A whole-slide foundation model for digital pathology from real-world data (opens in new tab) Nature
Hanwen Xu (opens in new tab), Naoto Usuyama (opens in new tab), Jaspreet Bagga, Sheng Zhang, Rajesh Rao, Tristan Naumann, Cliff Wong, Zelalem Gero (opens in new tab), Javier González, Yu Gu (opens in new tab), Yanbo Xu (opens in new tab), Mu Wei (opens in new tab), Wenhui Wang, Shuming Ma, Furu Wei, Jianwei Yang (opens in new tab), Chunyuan Li (opens in new tab), Jianfeng Gao, Jaylen Rosemon, Tucker Bower, Soohee Lee, Roshanthi Weerasinghe, Bill J. Wright, Ari Robicsek, Brian Piening, Carlo Bifulco, Sheng Wang (opens in new tab), Hoifung Poon
[ Model (opens in new tab) | Data (opens in new tab) ] - Multimodal AI generates virtual population for tumor microenvironment modeling (opens in new tab) Cell
Jeya Maria Jose Valanarasu, Hanwen Xu (opens in new tab), Naoto Usuyama (opens in new tab), Chanwoo Kim, Cliff Wong, Peniel Argaw, Racheli Ben Shimol, Angela Crabtree, Kevin Matlock, Alexandra Q. Bartlett, Jaspreet Bagga, Yu Gu (opens in new tab), Sheng Zhang, Tristan Naumann, Bernard A. Fox, Bill Wright, Ari Robicsek, Brian Piening, Carlo Bifulco, Sheng Wang (opens in new tab), Hoifung Poon - UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (opens in new tab) ICLR 2024
Wenxuan Zhou (opens in new tab)*, Sheng Zhang*, Yu Gu (opens in new tab), Muhao Chen (opens in new tab), Hoifung Poon (*equal contribution)
[ Demo (opens in new tab) | Model (opens in new tab) | MSR Podcast ] - AMR Parsing as Sequence-to-Graph Transduction (opens in new tab) ACL 2019 Best Paper Nominee (opens in new tab)
Sheng Zhang, Xutai Ma, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Code (opens in new tab) | BibTex (opens in new tab) ]
Click for full publications
- OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning (opens in new tab) CVPR 2026
Timothy Ossowski (opens in new tab)*, Sheng Zhang*, Qianchu Liu, Guanghui Qin (opens in new tab), Reuben Tan (opens in new tab), Tristan Naumann, Junjie Hu (opens in new tab), Hoifung Poon (*equal contribution)
[ Model (opens in new tab) | Blog (opens in new tab) | Data (opens in new tab) ] - Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration (opens in new tab)
James Y. Huang (opens in new tab)*, Sheng Zhang*, Qianchu Liu, Guanghui Qin (opens in new tab), Tinghui Zhu (opens in new tab), Tristan Naumann, Muhao Chen (opens in new tab), Hoifung Poon (*equal contribution)
[ Blog (opens in new tab) ] - Scaling medical imaging report generation with multimodal reinforcement learning (opens in new tab)
Qianchu Liu*, Sheng Zhang*, Guanghui Qin (opens in new tab)*, Yu Gu (opens in new tab), Ying Jin, Sam Preston, Yanbo Xu (opens in new tab), Sid Kiblawi, Wen-wai Yim (opens in new tab), Timothy Ossowski (opens in new tab), Tristan Naumann, Mu Wei (opens in new tab), Hoifung Poon (*equal contribution)
[ MSR Blog ] - MetaScale: Test-Time Scaling with Evolving Meta-Thoughts (opens in new tab) ACL 2026
Qin Liu (opens in new tab), Wenxuan Zhou (opens in new tab), Nan Xu (opens in new tab), James Y. Huang (opens in new tab), Fei Wang (opens in new tab), Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab) - Multimodal AI generates virtual population for tumor microenvironment modeling (opens in new tab) Cell
Jeya Maria Jose Valanarasu, Hanwen Xu (opens in new tab), Naoto Usuyama (opens in new tab), Chanwoo Kim, Cliff Wong, Peniel Argaw, Racheli Ben Shimol, Angela Crabtree, Kevin Matlock, Alexandra Q. Bartlett, Jaspreet Bagga, Yu Gu (opens in new tab), Sheng Zhang, Tristan Naumann, Bernard A. Fox, Bill Wright, Ari Robicsek, Brian Piening, Carlo Bifulco, Sheng Wang (opens in new tab), Hoifung Poon - X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains (opens in new tab)
Qianchu Liu*, Sheng Zhang*, Guanghui Qin (opens in new tab)*, Timothy Ossowski (opens in new tab), Yu Gu (opens in new tab), Ying Jin, Sid Kiblawi, Sam Preston, Mu Wei (opens in new tab), Paul Vozila, Tristan Naumann, Hoifung Poon (*equal contribution)
[ Project Page (opens in new tab) ] - Generative Medical Event Models Improve with Scale (opens in new tab)
Shane Waxler, Paul Blazek, Davis White, Daniel Sneider, Kevin Chung, Mani Nagarathnam, Patrick Williams, Hank Voeller, Karen Wong, Matthew Swanhorst, Sheng Zhang, Naoto Usuyama (opens in new tab), Cliff Wong, Tristan Naumann, Hoifung Poon, Andrew Loza, Daniella Meeker, Seth Hain, Rahul Shah - Exploring Scaling Laws for EHR Foundation Models (opens in new tab)
Sheng Zhang, Qin Liu (opens in new tab), Naoto Usuyama (opens in new tab), Cliff Wong, Tristan Naumann, Hoifung Poon - Med-RLVR: Emerging Medical Reasoning from a 3B base model via Reinforcement Learning (opens in new tab)
Sheng Zhang, Qianchu Liu, Guanghui Qin (opens in new tab), Tristan Naumann, Hoifung Poon - Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation (opens in new tab) Nature Communications
Juan Manuel Zambrano Chaves*, Shih-Cheng Huang*, Yanbo Xu (opens in new tab)*, Hanwen Xu (opens in new tab)*, Naoto Usuyama (opens in new tab)*, Sheng Zhang*, Fei Wang (opens in new tab), Yujia Xie, Mahmoud Khademi, Ziyi Yang, Hany Awadalla, Julia Gong, Houdong Hu, Jianwei Yang (opens in new tab), Chunyuan Li (opens in new tab), Jianfeng Gao, Yu Gu (opens in new tab), Cliff Wong, Mu Wei (opens in new tab), Tristan Naumann, Muhao Chen (opens in new tab), Matthew P. Lungren (opens in new tab), Akshay Chaudhari, Serena Yeung-Levy, Curtis P. Langlotz, Sheng Wang (opens in new tab), Hoifung Poon (*equal contribution) - From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning (opens in new tab) NAACL 2025
Nan Xu (opens in new tab), Fei Wang (opens in new tab), Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab) - Biomedical Natural Language Processing in the Era of Large Language Models (opens in new tab) Annual Review of Biomedical Data Science
Naoto Usuyama (opens in new tab), Cliff Wong, Sheng Zhang, Tristan Naumann, Hoifung Poon - The Illusion of Readiness in Health AI (opens in new tab)
Yu Gu (opens in new tab), Jingjing Fu, Xiaodong Liu (opens in new tab), Jeya Maria Jose Valanarasu, Noel Codella, Reuben Tan (opens in new tab), Qianchu Liu, Ying Jin, Sheng Zhang, Jinyu Wang, Rui Wang, Lei Song, Guanghui Qin (opens in new tab), Naoto Usuyama (opens in new tab), Cliff Wong, Hao Cheng (opens in new tab), Ho Hin Lee, Praneeth Sanapathi, Sarah Hilado, Tristan Naumann, Javier Alvarez-Valle, Jiang Bian, Mu Wei (opens in new tab), Khalil Malik, Lidong Zhou, Jianfeng Gao, Eric Horvitz (opens in new tab), Matthew P. Lungren (opens in new tab), Doug Burger, Eric Topol, Hoifung Poon, Paul Vozila - Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale (opens in new tab)
Cliff Wong, Sam Preston, Qianchu Liu, Zelalem Gero (opens in new tab), Jaspreet Bagga, Sheng Zhang, Shrey Jain, Theodore Zhao (opens in new tab), Yu Gu (opens in new tab), Yanbo Xu (opens in new tab), Sid Kiblawi, Srinivasan Yegnasubramanian, Taxiarchis Botsis, Marvin Borja, Luis M. Ahumada, Joseph C. Murray, Guo Hui Gan, Roshanthi Weerasinghe, Kristina Young, Rom Leidner, Brian Piening, Carlo Bifulco, Tristan Naumann, Mu Wei (opens in new tab), Hoifung Poon - ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation (opens in new tab)
Qin Liu (opens in new tab), Jacob Dineen, Yuxi Huang, Sheng Zhang, Hoifung Poon, Ben Zhou (opens in new tab), Muhao Chen (opens in new tab) - Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guided Visual Selection (opens in new tab)
Bangzheng Li, Fei Wang (opens in new tab), Wenxuan Zhou (opens in new tab), Nan Xu (opens in new tab), Ben Zhou (opens in new tab), Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab) - OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas (opens in new tab)
James Y. Huang (opens in new tab), Wenxuan Zhou (opens in new tab), Nan Xu (opens in new tab), Fei Wang (opens in new tab), Qin Liu (opens in new tab), Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab) - Pretraining Patient Foundation Models on Multimodal Patient Journeys (opens in new tab) NeurIPS 2025 Workshop on Learning from Time Series for Health
Daniel P. Jeong, Suhana Bedi, Cliff Wong, Sheng Zhang, Jeya Maria Jose Valanarasu, Qianchu Liu, Reuben Tan (opens in new tab), Zelalem Gero (opens in new tab), Jaspreet Bagga, Juan Manuel Zambrano Chaves, Naoto Usuyama (opens in new tab), Hanwen Xu (opens in new tab), Roshanthi Weerasinghe, Rom Leidner, Brian D. Piening, Carlo Bifulco, Tristan Naumann, Hoifung Poon - Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents (opens in new tab)
Reuben Tan (opens in new tab), Baolin Peng, Zhengyuan Yang, Hao Cheng (opens in new tab), Oier Mees, Theodore Zhao (opens in new tab), Andrea Tupini, Isar Meijier, Qianhui Wu, Yuncong Yang, Lars Liden, Yu Gu (opens in new tab), Sheng Zhang, Xiaodong Liu (opens in new tab), Lijuan Wang, Marc Pollefeys, Yong Jae Lee, Jianfeng Gao - Learning Robust Representations for Medical Images via Unifying (Self-)Supervisions (opens in new tab) ICLR 2025
Xiaoxuan He, Xufang Luo, Yifan Yang, Xinyang Jiang, Zilong Wang, Naoto Usuyama (opens in new tab), Sheng Zhang, Hoifung Poon, Yuqing Yang, Dongsheng Li, Lili Qiu - LLaVA-Rad MIMIC-CXR Annotations (opens in new tab) PhysioNet
Juan Manuel Zambrano Chaves, Shih-Cheng Huang, Yanbo Xu (opens in new tab), Hanwen Xu (opens in new tab), Naoto Usuyama (opens in new tab), Sheng Zhang, Fei Wang (opens in new tab), Yujia Xie, Mahmoud Khademi, Ziyi Yang, Hany Awadalla, Julia Gong, Houdong Hu, Jianwei Yang (opens in new tab), Chunyuan Li (opens in new tab), Jianfeng Gao, Yu Gu (opens in new tab), Cliff Wong, Mu Wei (opens in new tab), Tristan Naumann, Muhao Chen (opens in new tab), Matthew P. Lungren (opens in new tab), Akshay Chaudhari, Serena Yeung, Curtis Langlotz, Sheng Wang (opens in new tab), Hoifung Poon - BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs (opens in new tab) NEJM AI
Sheng Zhang*, Yanbo Xu (opens in new tab)*, Naoto Usuyama (opens in new tab), Hanwen Xu (opens in new tab), Jaspreet Bagga (opens in new tab), Robert Tinn (opens in new tab), Sam Preston, Rajesh Rao, Mu Wei (opens in new tab), Naveen Valluri (opens in new tab), Cliff Wong, Andrea Tupini, Yu Wang, Matt Mazzola, Swadheen Shukla, Lars Liden, Jianfeng Gao, Angela Crabtree, Brian Piening, Carlo Bifulco, Matthew P. Lungren (opens in new tab), Tristan Naumann, Sheng Wang (opens in new tab), Hoifung Poon (*equal contribution)
[ Model (opens in new tab) | Data (opens in new tab) ] - mDPO: Conditional Preference Optimization for Multimodal Large Language Models (opens in new tab) EMNLP 2024
Fei Wang (opens in new tab), Wenxuan Zhou (opens in new tab), James Y. Huang (opens in new tab), Nan Xu (opens in new tab), Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab)
[ Code (opens in new tab) ] - Offset Unlearning for Large Language Models (opens in new tab) TMLR
James Y. Huang (opens in new tab), Wenxuan Zhou (opens in new tab), Fei Wang (opens in new tab), Fred Morstatter (opens in new tab), Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab) - MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging (opens in new tab)
Noel Codella, Ying Jin, Shrey Jain, Yu Gu (opens in new tab), Ho Hin Lee, Asma Ben Abacha, Alberto Santamaria-Pang, Will Guyman, Naiteek Sangani, Sheng Zhang, Hoifung Poon, Stephanie L. Hyland (opens in new tab), Shruthi Bannur, Javier Alvarez-Valle, Xue Li, John Garrett, Alan McMillan, Gaurav Rajguru, Madhu Maddi, Nilesh Vijayrania, Rehaan Bhimai, Nick Mecklenburg, Rupal Jain, Daniel Holstein, Naveen Gaur, Vijay Aski, Jenq-Neng Hwang, Thomas Lin, Ivan Tarapov, Matthew P. Lungren (opens in new tab), Mu Wei (opens in new tab) - From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond (opens in new tab)
Harsha Nori, Naoto Usuyama (opens in new tab), Nicholas King, Scott Mayer McKinney, Xavier Fernandes, Sheng Zhang, Eric Horvitz (opens in new tab) - MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering (opens in new tab)
Robert Osazuwa Ness, Katie Matton, Hayden Helm, Sheng Zhang, Junaid Bajwa, Carey E. Priebe, Eric Horvitz (opens in new tab) - A whole-slide foundation model for digital pathology from real-world data (opens in new tab) Nature
Hanwen Xu (opens in new tab), Naoto Usuyama (opens in new tab), Jaspreet Bagga, Sheng Zhang, Rajesh Rao, Tristan Naumann, Cliff Wong, Zelalem Gero (opens in new tab), Javier González, Yu Gu (opens in new tab), Yanbo Xu (opens in new tab), Mu Wei (opens in new tab), Wenhui Wang, Shuming Ma, Furu Wei, Jianwei Yang (opens in new tab), Chunyuan Li (opens in new tab), Jianfeng Gao, Jaylen Rosemon, Tucker Bower, Soohee Lee, Roshanthi Weerasinghe, Bill J. Wright, Ari Robicsek, Brian Piening, Carlo Bifulco, Sheng Wang (opens in new tab), Hoifung Poon
[ Model (opens in new tab) | Data (opens in new tab) ] - UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (opens in new tab) ICLR 2024
Wenxuan Zhou (opens in new tab)*, Sheng Zhang*, Yu Gu (opens in new tab), Muhao Chen (opens in new tab), Hoifung Poon (*equal contribution)
[ Demo (opens in new tab) | Model (opens in new tab) | MSR Podcast ] - Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries (opens in new tab)
Zelalem Gero (opens in new tab), Chandan Singh (opens in new tab), Yiqing Xie (opens in new tab), Sheng Zhang, Tristan Naumann, Jianfeng Gao, Hoifung Poon - DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation (opens in new tab) ACL 2024
Yiqing Xie (opens in new tab), Sheng Zhang, Hao Cheng (opens in new tab), Pengfei Liu (opens in new tab), Zelalem Gero (opens in new tab), Cliff Wong, Tristan Naumann, Hoifung Poon, Carolyn Rose (opens in new tab)
[ DocLens (opens in new tab) ] - T-Rex: Text-assisted Retrosynthesis Prediction (opens in new tab)
Yifeng Liu, Hanwen Xu (opens in new tab), Tangqi Fang, Haocheng Xi, Zixuan Liu, Sheng Zhang, Hoifung Poon, Sheng Wang (opens in new tab) - MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding (opens in new tab)
Fei Wang (opens in new tab), Xingyu Fu, James Y. Huang (opens in new tab), Zekun Li, Qin Liu (opens in new tab), Xiaogeng Liu, Mingyu Derek Ma, Nan Xu (opens in new tab), Wenxuan Zhou (opens in new tab), Kai Zhang, Tianyi Lorena Yan, Wenjie Jacky Mo, Hsiang-Hui Liu, Pan Lu, Chunyuan Li (opens in new tab), Chaowei Xiao, Kai-Wei Chang, Dan Roth, Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab) - LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day (opens in new tab) NeurIPS 2023 (Spotlight)
Chunyuan Li (opens in new tab)*, Cliff Wong*, Sheng Zhang*, Naoto Usuyama (opens in new tab), Haotian Liu (opens in new tab), Jianwei Yang (opens in new tab), Tristan Naumann, Hoifung Poon, Jianfeng Gao (*equal contribution)
[ Project page (opens in new tab) ] - Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine (opens in new tab)
Harsha Nori*, Yin Tat Lee*, Sheng Zhang*, Dean Carignan, Richard Edgar, Nicolo Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama (opens in new tab), Chris White, Eric Horvitz (opens in new tab) (*equal contribution)
[ Blog | Code (opens in new tab) ] - BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys (opens in new tab)
Yu Gu (opens in new tab)*, Jianwei Yang (opens in new tab)*, Naoto Usuyama (opens in new tab), Chunyuan Li (opens in new tab), Sheng Zhang, Matthew P. Lungren (opens in new tab), Jianfeng Gao, Hoifung Poon (*equal contribution)
[ Project page (opens in new tab) ] - Scaling Clinical Trial Matching Using Large Language Models: A Case Study in Oncology (opens in new tab) MLHC 2023
Cliff Wong, Sheng Zhang, Yu Gu (opens in new tab), Christine Moung, Jacob Abel, Naoto Usuyama (opens in new tab), Roshanthi Weerasinghe, Brian Piening, Tristan Naumann, Carlo Bifulco, Hoifung Poon - Distilling Large Language Models for Biomedical Knowledge Extraction: A Case Study on Adverse Drug Events (opens in new tab)
Yu Gu (opens in new tab), Sheng Zhang, Naoto Usuyama (opens in new tab), Yonas Woldesenbet, Cliff Wong, Praneeth Sanapathi (opens in new tab), Mu Wei (opens in new tab), Naveen Valluri (opens in new tab), Erika Strandberg (opens in new tab), Tristan Naumann, Hoifung Poon - Context-faithful Prompting for Large Language Models (opens in new tab) EMNLP 2023 (Findings)
Wenxuan Zhou (opens in new tab), Sheng Zhang, Hoifung Poon, Muhao Chen (opens in new tab)
[ Code (opens in new tab) ] - Compositional Zero-Shot Domain Transfer with Text-to-Text Models (opens in new tab) TACL 2023
Fangyu Liu (opens in new tab), Qianchu Liu, Shruthi Bannur, Fernando Pérez-García, Naoto Usuyama (opens in new tab), Sheng Zhang, Tristan Naumann, Aditya Nori, Hoifung Poon, Javier Alvarez-Valle, Ozan Oktay, Stephanie L. Hyland (opens in new tab) - Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning (opens in new tab) ICLR 2023
Sheng Zhang, Hao Cheng (opens in new tab), Jianfeng Gao, Hoifung Poon
[ Code (opens in new tab) ] - Continual Contrastive Finetuning Improves Low-Resource Relation Extraction (opens in new tab) ACL 2023
Wenxuan Zhou (opens in new tab), Sheng Zhang, Tristan Naumann, Muhao Chen (opens in new tab), Hoifung Poon - Interactive Span Recommendation for Biomedical Text (opens in new tab) Clinical NLP Workshop 2023
Louis Blankemeier, Theodore Zhao (opens in new tab), Robert Tinn (opens in new tab), Sid Kiblawi, Yu Gu (opens in new tab), Akshay S. Chaudhari, Hoifung Poon, Sheng Zhang, Mu Wei (opens in new tab), Sam Preston - Precision Health in the Age of Large Language Models (opens in new tab) KDD 2023
Hoifung Poon, Tristan Naumann, Sheng Zhang, Javier González
[ Webpage (opens in new tab) ] - PISCES: A multi-modal data augmentation approach for drug combination synergy prediction (opens in new tab) Cell Genomics
Hanwen Xu (opens in new tab), Jiacheng Lin, Addie Woicik, Zixuan Liu, Jianzhu Ma, Sheng Zhang, Hoifung Poon, Liewei Wang, Sheng Wang (opens in new tab) - BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining (opens in new tab) Briefings in Bioinformatics
Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon, Tie-Yan Liu
[ Code (opens in new tab) ] - Knowledge-Rich Self-Supervision for Biomedical Entity Linking (opens in new tab) EMNLP 2022 (Findings)
Sheng Zhang*, Hao Cheng (opens in new tab)*, Shikhar Vashishth (opens in new tab)*, Cliff Wong, Jinfeng Xiao (opens in new tab), Xiaodong Liu (opens in new tab), Tristan Naumann, Jianfeng Gao, Hoifung Poon (*equal contribution)
[ Code (opens in new tab) ] - Modular Self-Supervision for Document-Level Relation Extraction (opens in new tab) EMNLP 2021
Sheng Zhang, Cliff Wong, Naoto Usuyama (opens in new tab), Sarthak Jain (opens in new tab), Tristan Naumann, Hoifung Poon - Joint Universal Syntactic and Semantic Parsing (opens in new tab) TACL 2021
Elias Stengel-Eskin (opens in new tab), Kenton Murray (opens in new tab), Sheng Zhang, Aaron Steven White (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Code (opens in new tab) ] - Universal Decompositional Semantic Parsing (opens in new tab) ACL 2020
Elias Stengel-Eskin (opens in new tab), Aaron Steven White (opens in new tab), Sheng Zhang, Benjamin Van Durme (opens in new tab)
[ Decomp (opens in new tab) | BibTex (opens in new tab) ] - Transductive Semantic Parsing (opens in new tab) Doctoral Dissertation
Sheng Zhang - The Universal Decompositional Semantics Dataset and Decomp Toolkit (opens in new tab) LREC 2020
Aaron Steven White (opens in new tab), Elias Stengel-Eskin (opens in new tab), Siddharth Vashishtha, Venkata Govindarajan, Dee Ann Reisinger (opens in new tab), Keisuke Sakaguchi (opens in new tab), Tim Vieira (opens in new tab), Sheng Zhang, Francis Ferraro (opens in new tab), Rachel Rudinger (opens in new tab), Kyle Rawlins (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Decomp (opens in new tab) | BibTex (opens in new tab) ] - Commonsense Inference in Natural Language Processing (COIN) — Shared Task Report (opens in new tab) Workshop on COIN at EMNLP-IJCNLP 2019
Simon Ostermann, Sheng Zhang, Michael Roth, Peter Clark - Broad-Coverage Semantic Parsing as Transduction (opens in new tab) EMNLP 2019
Sheng Zhang, Xutai Ma, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ BibTex (opens in new tab) ] - AMR Parsing as Sequence-to-Graph Transduction (opens in new tab) ACL 2019 Best Paper Nominee (opens in new tab)
Sheng Zhang, Xutai Ma, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Code (opens in new tab) | BibTex (opens in new tab) ] - Deep Generalized Canonical Correlation Analysis (opens in new tab) RepL4NLP at ACL 2019
Adrian Benton (opens in new tab), Huda Khayrallah (opens in new tab), Biman Gujral, Dee Ann Reisinger (opens in new tab), Sheng Zhang, Raman Arora (opens in new tab)
[ Code (opens in new tab) | BibTex (opens in new tab) ] - Unsupervised Deep Structured Semantic Models for Commonsense Reasoning (opens in new tab) NAACL 2019
Shuohang Wang (opens in new tab), Sheng Zhang, Yelong Shen (opens in new tab), Xiaodong Liu (opens in new tab), Jingjing Liu (opens in new tab), Jianfeng Gao, Jing Jiang (opens in new tab)
[ BibTex (opens in new tab) ] - ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension (opens in new tab)
Sheng Zhang, Xiaodong Liu (opens in new tab), Jingjing Liu (opens in new tab), Jianfeng Gao, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ LeaderBoard (opens in new tab) ] - Cross-lingual Decompositional Semantic Parsing (opens in new tab) EMNLP 2018
Sheng Zhang, Xutai Ma, Rachel Rudinger (opens in new tab), Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Supplements (opens in new tab) | BibTex (opens in new tab) ] - Neural Davidsonian Semantic Proto-role Labeling (opens in new tab) EMNLP 2018
Rachel Rudinger (opens in new tab), Adam Teichert (opens in new tab), Ryan Culkin, Sheng Zhang, Benjamin Van Durme (opens in new tab)
[ BibTex (opens in new tab) ] - Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds (opens in new tab) *SEM 2018
Sheng Zhang, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Code (opens in new tab) | BibTex (opens in new tab) ] - Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction (opens in new tab) *SEM 2018
Hongyuan Mei (opens in new tab)*, Sheng Zhang*, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab) (*equal contribution)
[ BibTex (opens in new tab) ] - Selective Decoding for Cross-lingual Open Information Extraction (opens in new tab) IJCNLP 2017
Sheng Zhang, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ BibTex (opens in new tab) ] - An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling (opens in new tab) IWCS 2017
Sheng Zhang, Rachel Rudinger (opens in new tab), Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Code (opens in new tab) | BibTex (opens in new tab) ] - MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models (opens in new tab) EACL 2017
Sheng Zhang, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Code (opens in new tab) | BibTex (opens in new tab) ] - Ordinal Common-sense Inference (opens in new tab) TACL 2017
Sheng Zhang, Kevin Duh (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Corpus (opens in new tab) | BibTex (opens in new tab) ] - Universal Decompositional Semantics on Universal Dependencies (opens in new tab) EMNLP 2016
Aaron Steven White (opens in new tab), Dee Ann Reisinger (opens in new tab), Keisuke Sakaguchi (opens in new tab), Tim Vieira (opens in new tab), Sheng Zhang, Rachel Rudinger (opens in new tab), Kyle Rawlins (opens in new tab), Benjamin Van Durme (opens in new tab)
[ Project Page (opens in new tab) | BibTex (opens in new tab) ] - Semantic Interpretation of Superlative Expressions via Structured Knowledge Bases (opens in new tab) ACL 2015
Sheng Zhang, Yansong Feng (opens in new tab), Songfang Huang, Kun Xu (opens in new tab), Zhe Han, Dongyan Zhao
[ BibTex (opens in new tab) ] - What Is the Longest River in the USA? Semantic Parsing for Aggregation Questions (opens in new tab) AAAI 2015
Kun Xu (opens in new tab), Sheng Zhang, Yansong Feng (opens in new tab), Dongyan Zhao
[ BibTex (opens in new tab) ] - Answering Natural Language Questions via Phrasal Semantic Parsing (opens in new tab) NLPCC 2014
Kun Xu (opens in new tab), Sheng Zhang, Yansong Feng (opens in new tab), Dongyan Zhao
[ BibTex (opens in new tab) ]
Tutorials
- Precision Health in the Age of Large Language Models (opens in new tab) KDD 2023
Hoifung Poon, Tristan Naumann, Sheng Zhang, Javier González
[ Webpage (opens in new tab) ]
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)