拖拽旋转 · 滚轮缩放 · 点击下钻
从这里开始
把第一次进入，变成第一步进展
不需要先理解全部板块。先选一种进入方式：定位起点、直接开始学习，或带着问题直达文章。
主题入口
已经知道自己要学什么时，直接进入板块即可。
继续阅读
从当前浏览器里的学习记录继续，或者从推荐入口重新开始。
学习记录仅保存在当前浏览器，不影响公开阅读。
空状态
还没有学习记录，先完成第一步就会形成自己的节奏。
如果你是第一次进入，先从 AI 认知基础或能力测评开始；之后首页会自动保留你的继续阅读与连续学习反馈。
练习工具
闪卡强化记忆，测验检验掌握
成就与勋章
记录每一步成长，解锁专业技能荣誉
学科大师
铜完美答题达人
铜连续学习
铜能力评估
银精选文章
S 级Awesome GraphRAG: Curated Papers, Benchmarks & Projects
Awesome-GraphRAG (GraphRAG Survey) This repository contains a curated list of resources on graph-based retrieval-augmented generation (GraphRAG), which are classified according to "A Survey of Graph...
约 14 分钟
LM Evaluation Harness: A Framework for Few-Shot Evaluation
Language Model Evaluation Harness Latest News [2025/12] CLI refactored with subcommands (run, ls, validate) and YAML config file support via --config. See the CLI Reference and Configuration Guide....
约 23 分钟
LightRAG: Simple and Fast Retrieval-Augmented Generation
LightRAG: Simple and Fast Retrieval-Augmented Generation News [2025.11][New Feature]: Integrated RAGAS for Evaluation and Langfuse for Tracing. Updated the API to return retrieved contexts alongside...
约 43 分钟
LlamaFactory: Unified Fine-Tuning for 100+ LLMs
Used by Amazon, NVIDIA, Aliyun, etc. Supporters Warp, the agentic terminal for developersAvailable for MacOS, Linux, & Windows Easily fine-tune 100+ large language models with zero-code CLI and Web...
约 19 分钟
TRL: Transformer Reinforcement Learning (RLHF/DPO)
TRL - Transformer Reinforcement Learning A comprehensive library to post-train foundation models What's New OpenEnv Integration: TRL now supports OpenEnv, the open-source framework from Meta for...
约 3 分钟
Unsloth: 2x Faster Fine-Tuning with 70% Less VRAM
Train gpt-oss, DeepSeek, Gemma, Qwen & Llama 2x faster with 70% less VRAM! Train for Free Notebooks are beginner friendly. Read our guide. Add dataset, run, then deploy your trained model. Model Free...
约 13 分钟