Shitao Xiao
Source-listed: Researcher; exact formal title unknown · Beijing Academy of Artificial Intelligence (BAAI)
- Multimodal AI
- Language models
- Information retrieval
Selected work
5- MMTEB: Massive Multilingual Text Embedding BenchmarkAuthor · 2025
- C-Pack: Packed Resources For General Chinese EmbeddingsFirst author · 2024
- OmniGen: Unified Image GenerationFirst author · 2025
- Long Context Compression with Activation BeaconContributor · 2024
- RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-EncoderFirst author · 2022