花了很久，才整理好的大模型学习路线......

Core Insights - The article emphasizes the growing interest in large model technologies, particularly in areas like VLA and VLM, and the high demand for talent skilled in RAG and AI Agent technologies [1][3] - The establishment of a community focused on large models aims to provide a platform for knowledge sharing and technical exchange among practitioners and learners in the field [6][8] Group 1: Community and Learning Opportunities - The "大模型之心Tech" community is designed to be a comprehensive platform that integrates video, text, learning paths, Q&A, and job exchange, with a goal of reaching nearly 10,000 members in two years [3][6] - The community invites experts from renowned universities and leading companies in the AI and internet sectors, creating a hub for cutting-edge technology discussions [6][68] - Members will have access to job recommendations and industry insights, facilitating connections with potential employers [8][9] Group 2: Learning Pathways - A detailed learning roadmap for large models has been compiled, covering various areas such as RAG, AI Agent, and multimodal models, catering to both beginners and advanced learners [7][11] - Specific learning routes include Graph RAG, AI Agent core technologies, and multimodal model training, providing structured resources for systematic learning [7][11] Group 3: Technical Resources - The community offers extensive resources on RAG, including benchmarks, reviews, and applications in AIGC, aimed at helping newcomers understand the technology [12][25] - For AI Agents, the community provides insights into the latest reviews, open-source repositories, and evaluation methods, further detailing subfields like multi-agent systems [27][33] - Resources on multimodal model training, including datasets and reinforcement learning techniques, are also available, with plans for continuous enrichment of these modules [44][55] Group 4: Engagement and Events - The community plans to host live sessions with industry leaders, allowing members to engage with top experts and revisit the content as needed [67] - A focus on job sharing and recruitment information will empower members to find relevant job opportunities in the field [68]