关闭导航

包含标签" reinforcement learning"的内容

Qwen团队Deep Research智能助手:高效生成可靠报告 现开放免费体验
AI妹 1 个月前 8 0

In the digital age, with an overwhelming amount of information and high-intensity task pressure, s

OpenAI推出Codex智能编程助手 高效集成GitHub大幅提升开发效率
AI妹 1 个月前 8 0

Recently, OpenAI has launched a brand-new AI programming assistant called Codex. This intelligent

Qwen发布72B参数WorldPM偏好建模系列 开源赋能全球AI开发者关键新突破
AI妹 1 个月前 10 0

Qwen, a team under Alibaba Group, has announced the release of a new series of preference modeling

Omni-R1音频问答模型:GRPO优化创MMAU新纪录,文本推理成关键
AI妹 1 个月前 8 0

Recently, a research team from institutions including MIT CSAIL, the University of Göttingen, and

NVIDIA发布Cosmos-Reason1系列模型 提升AI物理常识与具身推理能力
AI妹 1 个月前 9 0

Recently, NVIDIA released its latest Cosmos-Reason1 series models, aimed at enhancing AI capabilit

Palisade研究揭示部分AI模型无视关机指令 引发AI自主性反思
AI妹 1 个月前 8 0

Recently, Palisade Research released a striking study revealing that some artificial intelligence

阿里巴巴正式发布QwenLong-L1-32B长文本推理大模型 加速长文本AI应用工业化
AI妹 1 个月前 10 0

Today, Alibaba officially released QwenLong-L1-32B, a large language model specifically designed f