AI论文清单与解读
大模型论文清单
部分论文解读
- 1986-通过反向传播误差学习表示-Learning representations by back-propagating errors
- 1997-优化中的无免费午餐定理-No Free Lunch Theorems for Optimization
- 2012-使用深度卷积神经网络进行 ImageNet 分类-ImageNet Classification with Deep Convolutional Neural Networks
- 2014-对抗性攻击与防御-Explaining and Harnessing Adversarial Examples
- 2015-使用深度强化学习玩雅达利游戏-Playing Atari with Deep Reinforcement Learning
- 2014-生成对抗网络-Generative Adversarial Nets
- 2015-深度学习-Deep Learning
- 2015-用于图像识别的深度残差学习-Deep Residual Learning for Image Recognition
- 2017-注意力就是你所需要的一切-Attention Is All You Need
- 2017-近端策略优化算法-Proximal Policy Optimization Algorithms
- 2018-世界模型-World Models
- 2018-通过生成式预训练提升语言理解能力-Improving Language Understanding by Generative Pre-Training
- 2018-BERT:用于语言理解的深度双向 Transformer 预训练-BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- 2019-苦涩的教训-The Bitter Lesson
- 2020-神经语言模型的扩展法则-Scaling Laws for Neural Language Models
- 2020-语言模型是小样本学习者-Language Models are Few-Shot Learners
- 2020-上下文学习-Language Models are Few-Shot Learners
- 2020-检索增强生成-Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- 2021-自监督学习:智能的暗物质-Self-supervised Learning: The Dark Matter of Intelligence
- 2020-去噪扩散概率模型-Denoising Diffusion Probabilistic Models
- 2021-零样本文字到图像生成-Zero-Shot Text-to-Image Generation
- 2021-从自然语言监督中学习可迁移的视觉模型-Learning Transferable Visual Models From Natural Language Supervision
- 2021-Switch Transformers:通过简单高效的稀疏性扩展到万亿参数模型-Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- 2021-基础模型的机遇与风险-On the Opportunities and Risks of Foundation Models
- 2022-思维链提示-Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- 2022-基于人类反馈的强化学习-Training language models to follow instructions with human feedback
- 2022-大型语言模型的涌现能力-Emergent Abilities of Large Language Models
- 2022-宪法AI:来自AI反馈的无害性训练-Constitutional AI: Harmlessness from AI Feedback
- 2023-迷失在中间:大语言模型如何使用长上下文-Lost in the Middle: How Language Models Use Long Contexts
- 2023-AI对齐理论:从深度学习视角看对齐问题-The Alignment Problem from a Deep Learning Perspective
- 2023-AI编程能力-Evaluating Large Language Models Trained on Code / Competition-Level Code Generation with AlphaCode
- 2024-多模态大语言模型-Multimodal Large Language Models
- 2024-欢迎来到经验时代-Welcome to the Era of Experience