参考资料
优先阅读论文原文和官方文档。技术报告中的实验结论应结合模型版本、评估配置和发布日期理解。
面试题清单
- Simplilearn, 60+ Machine Learning Interview Questions and Answers, last updated Jun 18, 2026.
Transformer 与架构
- Vaswani et al., Attention Is All You Need
- Devlin et al., BERT
- Raffel et al., Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Su et al., RoFormer: Enhanced Transformer with Rotary Position Embedding
- Shazeer, Fast Transformer Decoding: One Write-Head is All You Need
- Ainslie et al., GQA: Training Generalized Multi-Query Transformer Models
- Shazeer, GLU Variants Improve Transformer
- Dao et al., FlashAttention
经典序列模型与词向量
- Hochreiter and Schmidhuber, Long Short-Term Memory
- Bahdanau et al., Neural Machine Translation by Jointly Learning to Align and Translate
- Mikolov et al., Efficient Estimation of Word Representations in Vector Space
- Mikolov et al., Distributed Representations of Words and Phrases and their Compositionality
- Dempster et al., Maximum Likelihood from Incomplete Data via the EM Algorithm
Scaling、训练与 MoE
- Kaplan et al., Scaling Laws for Neural Language Models
- Hoffmann et al., Training Compute-Optimal Large Language Models
- Fedus et al., Switch Transformers
- Rajbhandari et al., ZeRO
- Narayanan et al., Efficient Large-Scale Language Model Training on GPU Clusters
Qwen 与 DeepSeek
- Qwen Team, Qwen2 Technical Report
- Qwen Team, Qwen2.5 Technical Report
- DeepSeek-AI, DeepSeek-V2
- DeepSeek-AI, DeepSeek-V3 Technical Report
- DeepSeek-AI, DeepSeek-R1
RLHF 与推理强化学习
- Ouyang et al., Training Language Models to Follow Instructions with Human Feedback
- Christiano et al., Deep Reinforcement Learning from Human Preferences
- Schulman et al., Proximal Policy Optimization Algorithms
- Rafailov et al., Direct Preference Optimization
- Bai et al., Constitutional AI
- Yu et al., DAPO
- Qwen Team, Group Sequence Policy Optimization
Agent
- Yao et al., ReAct
- Schick et al., Toolformer
- Yao et al., Tree of Thoughts
- Shinn et al., Reflexion
- Yang et al., SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- Wang et al., OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- Wang et al., The OpenHands Software Agent SDK
- Hu, From Agent Loops to Structured Graphs
- Liu et al., AgentBench
- Zhou et al., WebArena
- Jimenez et al., SWE-bench
- A2A Project, Agent2Agent Protocol
- Model Context Protocol, Official Documentation
RAG
- Lewis et al., Retrieval-Augmented Generation
- Karpukhin et al., Dense Passage Retrieval
- Nogueira and Cho, Passage Re-ranking with BERT
- Gao et al., HyDE
- Liu et al., Lost in the Middle
- Asai et al., Self-RAG
- Edge et al., From Local to Global: A Graph RAG Approach
评估
- Hendrycks et al., Measuring Massive Multitask Language Understanding
- Srivastava et al., BIG-bench
- Chen et al., Evaluating Large Language Models Trained on Code
- Zheng et al., Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- Mialon et al., GAIA
- Xie et al., OSWorld