The General Artificial Intelligence (GenAI) Group is focusing on research of Large Foundation Models and General AI, Natural Language Processing, Speech Processing, Multimodal AI, and AI Agent.
In the past few years, we have published and open sourced pioneering and high-impact research works and models, including UniLM, InfoXLM, XLM-E, MiniLM(-2), (m)E5, Layout(X)LM(-3), WavLM, BEiT(-3), Kosmos(-2), VALL-E, DeepNet, LongNet, (Gated) RetNet, YOCO / Decoder-Decoder Architecture, 1-bit LLMs / BitNet (b1.58 | a4.8), Q-Sparse / Fully Sparsely-Activated LLMs, DIFF (Differential Transformer), …
Research Areas
- Foundation Models: LLMs/MLLMs
- General AI Fundamentals
- AI Agent
- NLP
- Speech
- Multimodal AI
微软亚洲研究院通用人工智能组专注于自然语言处理和通用人工智能领域的理论、模型、算法和应用的研究和创新。目前主要的研究兴趣包括：大语言模型，多模态大语言模型，通用人工智能，通用智能体，自然语言处理，语音处理，多模态人工智能等。