AI论文 SynthVLM: High-Efficiency and High-Quality Synthetic Data forVision Language Models[视觉语言模型的高效高质量合成数据]-AI论文 2024-11-19
AI论文 AGENTGYM:在不同环境中发展基于大型语言模型的代理[Evolving Large Language Model-based Agents across Diverse Environments]-AI论文 2024-11-02
AI论文 OpenAIo1复制之旅:旅程学习战略进展报告[O1 Replication Journey: A Strategic Progress Report – Part 1]-AI论文 2024-11-02
AI论文 思考快与慢的智能体:对话者-推理者架构[Agents Thinking Fast and Slow:A Talker-Reasoner Architecture]-AI论文 2024-11-02
AI论文 DeepMind:强化学习处理不正确的合成数据,使大模型数学推理效率提高八倍[RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold]-AI论文 2024-10-31