Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Andrew Zhao, Yiran Wu, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu e mais 2
De quem é
- Pennsylvania State Universityafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- Large Language Models for Mathematical Reasoning: Progresses and ChallengesPennsylvania State University · 703 citações
- A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and TrustworthinessAmazon · 400 citações
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language ModelsAmazon · 273 citações
- Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language ModelsPennsylvania State University · 236 citações
- UniTok: a Unified Tokenizer for Visual Generation and UnderstandingPennsylvania State University · 176 citações