Michael Zeng
Microsoft (United States)(US)Microsoft (Germany)(DE)Microsoft Research (United Kingdom)(GB)
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Speech Recognition and Synthesis, Multimodal Machine Learning Applications, Speech and dialogue systems
Most-Cited Works
- → WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing(2022)1,450 cited
- → Florence: A New Foundation Model for Computer Vision(2021)340 cited
- → An Empirical Study of Training End-to-End Vision-and-Language Transformers(2022)308 cited
- → Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks(2024)168 cited
- → Few-shot Natural Language Generation for Task-Oriented Dialog(2020)157 cited
- → Automatic Prompt Optimization with “Gradient Descent” and Beam Search(2023)128 cited
- → A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining(2020)122 cited
- → Enhancing Factual Consistency of Abstractive Summarization(2021)122 cited
- → SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering(2018)118 cited
- → JAKET: Joint Pre-training of Knowledge Graph and Language Understanding(2022)113 cited