LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Yingzhe Peng, Gongrui Zhang, Miaosen Zhang, Zhiyuan You, Liu, Jie, Qipeng Zhu, Yang, Kai, Xingzhong Xu e mais 2
De quem é
Ant Groupafiliação declarada pelos autores, segundo o OpenAlex- Southeast Universityafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- SpectralGPT: Spectral Remote Sensing Foundation ModelChinese Academy of Sciences · 1.242 citações
- A Survey on Self-Supervised Learning: Algorithms, Applications, and Future TrendsAlibaba Group · 979 citações
- VLMEvalKit: An Open-Source ToolKit for Evaluating Large Multi-Modality ModelsSoutheast University · 706 citações
- AnyDoor: Zero-shot Object-level Image CustomizationAnt Group · 572 citações
- SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation ImageryAnt Group · 549 citações
- LLMs for knowledge graph construction and reasoning: recent capabilities and future opportunitiesAnt Group · 531 citações