Kosmos-2: Grounding Multimodal Large Language Models to the World
Research paper by Zhiliang Peng and collaborators. Published 2023-06-26. Topics: Multimodal Large Language Model, MLLM, refer expressions, Markdown, location tokens.
Resource information
- Authors
- Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, Furu Wei
- Research topics
- Multimodal Large Language Model, MLLM, refer expressions, Markdown, location tokens, grounded image-text pairs, multimodal grounding, referring expression comprehension, phrase grounding, multimodal referring, referring expression generation, perception-language tasks
- Publication date
- 2023-06-26
- Publication
- arXiv
- Last record update
- Nov 3, 2026