返回首页
DeepSeek-R1
找到 2 篇关于此标签的文章
DeepSeek-R1Qwen2.5-Math
Mathematical Methods and Human Thought in the Age of AI
arxiv paper examines how AI reshapes mathematical reasoning and what it means for human cognitive processes.
Apr 42 分钟
GRPODeepSeek-R1
From GRPO to BCR: The Battle to Cut LLM Reasoning Costs
New training methods like Sample Routing and BCR target wasteful chain-of-thought token usage, cutting inference costs significantly.
Apr 42 分钟