• 🧠 逻辑之迷:揭秘思维陷阱的奥秘

  • Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability

  • AI技术的新突破:复旦研究团队大幅提升模型上下文理解能力

  • FP8-LM: Training FP8 Large Language Models 探索FP8低精度训练:大型语言模型(LLMs)的新篇章

  • Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning

人生梦想 - 关注前沿的计算机技术 acejoy.com