🤖 AI学习必读100篇重要论文

按时间顺序整理 | 包含论文名称、作者、年份和下载链接

🏛️ 基础理论时期 (1950-1989)

#	年份	论文名称	作者
1	1950	Computing Machinery and Intelligence	Alan Turing
2	1956	A Proposal for the Dartmouth AI Summer Research Project	John McCarthy, et al.
3	1966	MIT Speech Recognition system - ELIZA	Joseph Weizenbaum
4	1969	Perceptrons: An Introduction to Computational Geometry	Marvin Minsky, Seymour Papert
5	1974	A Theory of the Learnable	Leslie Valiant
6	1986	Learning Representations by Back-Propagating Errors	David Rumelhart, Geoffrey Hinton, Ronald Williams
7	1989	Backpropagation Applied to Handwritten Zip Code Recognition	Yann LeCun, et al.

🔬 统计学习与早期深度学习 (1990-2011)

#	年份	论文名称	作者
8	1995	Learning in the Presence of Concept Drift and Hidden Contexts	Leslie Valiant
9	1997	Long Short-Term Memory (LSTM)	Sepp Hochreiter, Jürgen Schmidhuber
10	1998	Gradient-Based Learning Applied to Document Recognition	Yann LeCun, Léon Bottou, Yoshua Bengio
11	1998	Boosting: A Weak Learning Algorithm	Yoav Freund, Robert Schapire
12	2001	Random Forests	Leo Breiman
13	2002	An Improved Boosting Algorithm	Alexander Grove, Dale Schuurmans
14	2003	A Tutorial on Support Vector Machines	Nello Cristianini, John Shawe-Taylor
15	2006	A Fast Learning Algorithm for Deep Belief Nets	Geoffrey Hinton, Simon Osindero, Yee-Whye Teh
16	2008	Sparse Feature Learning for Deep Belief Networks	Marc'Aurelio Ranzato, et al.
17	2010	Variational Learning for Digits	A. Mnih, K. Kavukcuoglu
18	2011	Neural Networks for NLP	Richard Socher, et al.

🚀 深度学习爆发期 (2012-2016)

#	年份	论文名称	作者
19	2012	ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)	Alex Krizhevsky, Ilya Sutskever, Geoffrey Hinton
20	2013	Efficient Estimation of Word Representations in Vector Space (Word2Vec)	Tomas Mikolov, et al.
21	2013	Playing Atari with Deep Reinforcement Learning	Volodymyr Mnih, et al.
22	2014	Generative Adversarial Networks (GAN)	Ian Goodfellow, et al.
23	2014	Sequence to Sequence Learning with Neural Networks	Ilya Sutskever, Oriol Vinyals, Quoc V. Le
24	2014	Neural Machine Translation by Jointly Learning to Align and Translate	Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio
25	2014	Dropout: A Simple Way to Prevent Neural Networks from Overfitting	Nitish Srivastava, et al.
26	2015	Batch Normalization: Accelerating Deep Network Training	Sergey Ioffe, Christian Szegedy
27	2015	Deep Residual Learning for Image Recognition (ResNet)	Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
28	2015	Very Deep Convolutional Networks for Large-Scale Image Recognition (VGGNet)	Karen Simonyan, Andrew Zisserman
29	2015	Spatial Transformer Networks	Max Jaderberg, et al.
30	2016	Mastering the Game of Go with Deep Neural Networks and Tree Search (AlphaGo)	David Silver, Aja Huang, et al.
31	2016	FastText: Bag of Tricks for Efficient Text Classification	Armand Joulin, et al.
32	2016	WaveNet: A Generative Model for Raw Audio	Aaron van den Oord, et al.

⚡ Transformer与预训练模型时代 (2017-2020)

#	年份	论文名称	作者
33	2017	Attention Is All You Need (Transformer)	Ashish Vaswani, Noam Shazeer, et al.
34	2017	Neural Machine Translation with Latent Alignment	Dzmitry Bahdanau, et al.
35	2017	Fast and Accurate Reading Comprehension by Neural Network	Romain Gloannec, et al.
36	2018	BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding	Jacob Devlin, Ming-Wei Chang, et al.
37	2018	Improving Language Understanding by Generative Pre-Training (GPT)	Alec Radford, et al.
38	2018	GLUE: A Multi-Task Benchmark and Evaluation for NLP	Alex Wang, et al.
39	2019	XLNet: Generalized Autoregressive Pretraining for Language Understanding	Zhilin Yang, et al.
40	2019	Visualizing and Measuring the Geometry of BERT	Ian Tenney, et al.
41	2019	RoBERTa: A Robustly Optimized BERT Pretraining Approach	Yinhan Liu, et al.
42	2019	ControlNet: Conditional Neural Networks	Lvmin Zhang, et al.
43	2020	Language Models are Few-Shot Learners (GPT-3)	Tom Brown, et al.
44	2020	Image GPT	Xi Chen, et al.
45	2020	YOLOv4: Optimal Speed and Accuracy of Object Detection	Alexey Bochkovskiy, et al.
46	2020	Bootstrap Your Own Latent (BYOL)	Jean-Bastien Grill, et al.
47	2020	SimCLRv2: Big Self-Supervised Models are Strong Semi-Supervised Learners	Ting Chen, et al.
48	2020	An Image is Worth 16x16 Words: Transformers for Image Recognition (ViT)	Alexey Dosovitskiy, et al.
49	2020	Exploring the Limits of Transfer Learning with T5	Colin Raffel, et al.
50	2020	Denoising Diffusion Probabilistic Models	Jonathan Ho, Ajay Jain, Pieter Abbeel
51	2020	Score-Based Generative Modeling through Stochastic Differential Equations	Yang Song, et al.

🤖 大模型与生成式AI时代 (2021-2022)

#	年份	论文名称	作者
52	2021	Highly Accurate Protein Structure Prediction with AlphaFold2	John Jumper, Richard Evans, et al.
53	2021	Learning Transferable Visual Models From Natural Language Supervision (CLIP)	Alec Radford, et al.
54	2021	Swin Transformer: Hierarchical Vision Transformer using Shifted Windows	Ze Liu, et al.
55	2021	Emerging Properties in Self-Supervised Vision Transformers (DINO)	Mathilde Caron, et al.
56	2021	DALL-E: Zero-Shot Text-to-Image Generation	Aditya Ramesh, et al.
57	2021	Chain-of-Thought Prompting Elicits Reasoning in Large Language Models	Jason Wei, et al.
58	2021	Noised CLIP: CLIP with Positive-Negative Contrastive Learning	Dieuwke Hupkes, et al.
59	2021	LLaMA: Open and Efficient Foundation Language Models	Hugo Touvron, et al.
60	2021	OPT: Open Pre-trained Transformer Language Models	Susan Zhang, et al.
61	2021	Training Compute-Optimal Large Language Models (Chinchilla)	Jordan Hoffmann, et al.
62	2022	Self-consistency Improves Chain of Thought Reasoning	Xuezhi Wang, et al.
63	2022	PaLM: Scaling Language Modeling with Pathways	Aakanksha Chowdhery, et al.
64	2022	Hierarchical Text-Conditional Image Generation with CLIP Latents (DALL-E 2)	Aditya Ramesh, et al.
65	2022	Make-An-Animation	Yuan Amou, et al.
66	2022	Emergent Abilities of Large Language Models	Jason Wei, et al.
67	2022	A ConvNet for the 2020s (ConvNeXt)	Zhuang Liu, et al.
68	2022	DeiT III: Revenge of the ViT	Hugo Touvron, et al.
69	2022	GiT: Graph Transformer for Graph Classification	Jiaxuan You, et al.
70	2022	RLHF: Training Language Models to Follow Instructions with Human Feedback	Long Ouyang, et al.
71	2022	Stable Diffusion: High-Resolution Image Synthesis with Latent Diffusion Models	Robin Rombach, et al.

🌟 AGI与大模型突破期 (2023-2024)

#	年份	论文名称	作者
72	2023	GPT-4 Technical Report	OpenAI
73	2023	LLaMA 2: Open Foundation and Fine-Tuned Chat Models	Hugo Touvron, et al.
74	2023	LLaMA-Adapter V2: Large Language Models with Visual Instruction Tuning	Peng Gao, et al.
75	2023	QLoRA: Efficient Finetuning of Quantized LLMs	Tim Dettmers, et al.
76	2023	FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness	Tri Dao, et al.
77	2023	Toolformer: Language Models Can Teach Themselves to Use Tools	Timo Schick, et al.
78	2023	Segment Anything Model (SAM)	Alexander Kirillov, et al.
79	2023	Llama 3 (Meta AI)	Meta AI
80	2023	Mistral 7B	Albert Jiang, et al.
81	2023	Mixtral of Experts	Albert Jiang, et al.
82	2023	MiniGPT-4: Enhancing Vision Language Understanding	Deyao Zhu, et al.
83	2023	LLaVA: Visual Instruction Tuning	Haotian Liu, et al.
84	2023	Multimodal Large Language Models: A Survey	Yongth P, et al.
85	2024	DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model	DeepSeek Team
86	2024	Qwen2 Technical Report	Alibaba
87	2024	DINOv2: Self-Supervised Vision Transformers	Maxime Oquab, et al.
88	2024	Sora: Video Generation from Text	OpenAI
89	2024	Llama 3.1 405B	Meta AI
90	2024	The Llama 3 Herd of Models	Meta AI
91	2024	Gemini 1.5: Unlocking Multimodal Long-Context Understanding	Google DeepMind
92	2024	DeepSeek-R1: Incentivizing Reasoning Capability in LLMs	DeepSeek Team
93	2024	o1: OpenAI Reasoning Model	OpenAI
94	2024	ReFT: Reasoning with Fine-Tuned Language Models	Stanford NLP

🔮 前沿研究方向 (2024-2025)

#	年份	论文名称	作者
95	2024	Agent Q:引导LLM进行自我改进	Meta AI
96	2024	Claude 3.5: Computer Use	Anthropic
97	2024	World Models: Generative AI for 3D Scenes	Kabra N, et al.
98	2025	DeepSeek-R2	DeepSeek Team
99	2025	Gemini 2.0	Google DeepMind
100	2025	o3-mini: OpenAI Reasoning Model	OpenAI

说明：
• 本列表按时间顺序排列，从1950年图灵测试到2025年最新研究
• 大部分论文可通过 arXiv 免费下载，部分链接可能需要科学上网
• 建议按时代分组学习：基础理论 → 深度学习 → Transformer → 大模型
• 更新日期：2025年3月