大模型之心Tech知识星球

Search documents
关于大模型和自动驾驶的一切
自动驾驶之心· 2025-09-15 23:33
Group 1 - The article emphasizes the growing interest in large model technologies, particularly in areas such as RAG (Retrieval-Augmented Generation), AI Agents, multimodal large models (pre-training, fine-tuning, reinforcement learning), and optimization for deployment and inference [1] - A community named "Large Model Heart Tech" is being established to focus on these technologies and aims to become the largest domestic community for large model technology [1] - The community is also creating a knowledge platform to provide industry and academic information, as well as to cultivate talent in the field of large models [1] Group 2 - The article describes the community as a serious content-driven platform aimed at nurturing future leaders [2]
推荐一个大模型AI私房菜!
自动驾驶之心· 2025-08-23 16:03
Group 1 - The article emphasizes the growing interest in large model technologies, particularly in areas such as RAG (Retrieval-Augmented Generation), AI Agents, multimodal large models (pre-training, fine-tuning, reinforcement learning), and optimization for deployment and inference [1] - A community named "Large Model Heart Tech" is being established to focus on these technologies and aims to become the largest domestic community for large model technology [1] - The community is also creating a knowledge platform to provide industry and academic information, as well as to cultivate talent in the field of large models [1] Group 2 - The article describes the community as a serious content-driven platform aimed at nurturing future leaders [2]
聊一聊多模态的交叉注意力机制
自动驾驶之心· 2025-08-22 16:04
作者 | Trancy Wang 编辑 | 大模型之心Tech 原文链接: https://zhuanlan.zhihu.com/p/1939104588109156480 点击下方 卡片 ,关注" 大模型之心Tech "公众号 戳我-> 领取大模型巨卷干货 >> 点击进入→ 大模型没那么大Tech技术交流群 本文只做学术分享,如有侵权,联系删文 ,自动驾驶课程学习与技术交流群事宜,也欢迎添加小助理微信AIDriver004做进一步咨询 一、交叉注意力在多模态里的位置 在多模态任务(图文匹配、VQA、视频理解、语音-图像结合等)里,光靠把不同模态的特征拼在一起是不够的。 我们希望让 一种模态主动去问另一种模态问题 ,而另一模态则 提供相关的上下文线索 。 交叉注意力(Cross-Attention)就是干这个的——它的核心思路是: Query(Q):主动方,要从另一模态获取信息; 公式和普通的 Transformer 注意力一样: 只是多模态版本里,Q 和 K/V 来自 不同来源 。 二、常见的四种设计方式 1. 单向交叉注意力(Single-direction Cross-Attention) 特点:只有一 ...
想学习更多大模型知识,如何系统的入门大?
自动驾驶之心· 2025-08-14 23:33
Group 1 - The article emphasizes the growing interest in large model technologies, particularly in areas such as RAG (Retrieval-Augmented Generation), AI Agents, multimodal large models (pre-training, fine-tuning, reinforcement learning), and optimization for deployment and inference [1] - A community named "Large Model Heart Tech" is being established to focus on these technologies and aims to become the largest domestic community for large model technology [1] - The community is also creating a knowledge platform to provide industry and academic information, as well as to cultivate talent in the field of large models [1] Group 2 - The article describes the community as a serious content-driven platform aimed at nurturing future leaders [2]
2025年大模型研究热点是什么?
自动驾驶之心· 2025-08-12 23:33
Group 1 - The article discusses the growing interest in large model technologies, particularly in areas such as RAG (Retrieval-Augmented Generation), AI Agents, multimodal large models (pre-training, fine-tuning, reinforcement learning), and optimization for deployment and inference [1] - A community named "Da Model Heart Tech" is being established to focus on large model technology and aims to become the largest domestic community for this field, providing talent and industry academic information [1] - The community encourages individuals interested in large model technology to join and participate in knowledge sharing and learning opportunities [1] Group 2 - The article emphasizes the importance of creating a serious content community that aims to cultivate future leaders [2]