SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Chen, Hardy, Haoqin Tu, Fali Wang, Hui Liu, Xianfeng Tang, Xinya Du, Yuyin Zhou, Cihang Xie
Who it is from
Amazonaffiliation declared by the authors, according to OpenAlex- Pennsylvania State Universityaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Large Language Models for Mathematical Reasoning: Progresses and ChallengesPennsylvania State University · 703 citations
- Absolute Zero: Reinforced Self-play Reasoning with Zero DataPennsylvania State University · 473 citations
- Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language ModelsAmazon · 420 citations
- A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and TrustworthinessAmazon · 400 citations
- Survey on Factuality in Large Language ModelsAmazon · 400 citations
- Multi-Modal Hallucination Control by Visual Information GroundingAmazon · 372 citations